{ "models": [ { "slug": "black-forest-labs/flux.2-klein-4b", "hf_slug": "", "updated_at": "2026-01-16T04:32:32.594442+00:00", "created_at": "2026-01-14T22:20:28.450361+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Klein 4B", "short_name": "FLUX.2 Klein 4B", "author": "black-forest-labs", "description": "FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.\n\nPricing is based on the output image. The first generated megapixel is charged $0.014. Each subsequent megapixel is charged $0.001.", "model_version_group_id": null, "context_length": 40960, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "black-forest-labs/flux.2-klein-4b", "supports_reasoning": false, "reasoning_config": {}, "features": { "reasoning_config": {}, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "9e2e48d5-2016-4e18-976a-c463146c7f9c", "name": "Black Forest Labs | black-forest-labs/flux.2-klein-4b", "context_length": 40960, "model": { "slug": "black-forest-labs/flux.2-klein-4b", "hf_slug": "", "updated_at": "2026-01-16T04:32:32.594442+00:00", "created_at": "2026-01-14T22:20:28.450361+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Klein 4B", "short_name": "FLUX.2 Klein 4B", "author": "black-forest-labs", "description": "FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.\n\nPricing is based on the output image. The first generated megapixel is charged $0.014. Each subsequent megapixel is charged $0.001.", "model_version_group_id": null, "context_length": 40960, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "black-forest-labs/flux.2-klein-4b", "supports_reasoning": false, "reasoning_config": {}, "features": { "reasoning_config": {}, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "black-forest-labs/flux.2-klein-4b", "model_variant_permaslug": "black-forest-labs/flux.2-klein-4b", "adapter_name": "BlackForestLabsAdapter", "provider_name": "Black Forest Labs", "provider_info": { "name": "Black Forest Labs", "displayName": "Black Forest Labs", "slug": "black-forest-labs", "baseUrl": "https://api.bfl.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "BlackForestLabsAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://bfl.ai&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "bfl" }, "provider_display_name": "Black Forest Labs", "provider_slug": "black-forest-labs", "provider_model_id": "flux-2-klein-4b", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "seed" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_output": "0.00000341796875", "discount": 0 }, "variable_pricings": [], "pricing_json": { "bfl:upstream_cost_cents": "1", "bfl:informational_output_megapixels": 0.014 }, "pricing_version_id": "2fe2f4f4-cec3-4788-9f83-47f3be988f17", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.2-codex", "hf_slug": "", "updated_at": "2026-01-14T18:06:58.161562+00:00", "created_at": "2026-01-14T16:48:35.067026+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2-Codex", "short_name": "GPT-5.2-Codex", "author": "openai", "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-codex-20260114", "supports_reasoning": true, "reasoning_config": { "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "low", "medium", "high", "xhigh" ], "default_reasoning_effort": "medium" }, "features": { "reasoning_config": { "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "low", "medium", "high", "xhigh" ], "default_reasoning_effort": "medium" }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "dff70494-a1eb-4be2-b61f-9b2277db56c9", "name": "OpenAI | openai/gpt-5.2-codex-20260114", "context_length": 400000, "model": { "slug": "openai/gpt-5.2-codex", "hf_slug": "", "updated_at": "2026-01-14T18:06:58.161562+00:00", "created_at": "2026-01-14T16:48:35.067026+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2-Codex", "short_name": "GPT-5.2-Codex", "author": "openai", "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-codex-20260114", "supports_reasoning": true, "reasoning_config": { "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "low", "medium", "high", "xhigh" ], "default_reasoning_effort": "medium" }, "features": { "reasoning_config": { "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "low", "medium", "high", "xhigh" ], "default_reasoning_effort": "medium" }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.2-codex", "model_variant_permaslug": "openai/gpt-5.2-codex-20260114", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.2-codex", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "seed", "max_tokens", "response_format", "structured_outputs", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000175", "completion": "0.000014", "input_cache_read": "0.000000175", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000175, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000014, "openai_responses:cached_prompt_tokens": 1.75e-7 }, "pricing_version_id": "bdea8a94-f94d-4281-b6a6-da5ffdf163c5", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "allenai/molmo-2-8b", "hf_slug": "allenai/Molmo2-8B", "updated_at": "2026-01-09T22:20:28.970761+00:00", "created_at": "2026-01-09T22:11:12.589713+00:00", "hf_updated_at": null, "name": "AllenAI: Molmo2 8B (free)", "short_name": "Molmo2 8B (free)", "author": "allenai", "description": "Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.", "model_version_group_id": null, "context_length": 36864, "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "allenai/molmo-2-8b-20260109", "supports_reasoning": false, "reasoning_config": {}, "features": { "reasoning_config": {}, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ed2677ef-e5a8-439e-8d23-0bc398915e61", "name": "Parasail | allenai/molmo-2-8b-20260109:free", "context_length": 36864, "model": { "slug": "allenai/molmo-2-8b", "hf_slug": "allenai/Molmo2-8B", "updated_at": "2026-01-09T22:20:28.970761+00:00", "created_at": "2026-01-09T22:11:12.589713+00:00", "hf_updated_at": null, "name": "AllenAI: Molmo2 8B", "short_name": "Molmo2 8B", "author": "allenai", "description": "Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.", "model_version_group_id": null, "context_length": 36864, "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "allenai/molmo-2-8b-20260109", "supports_reasoning": false, "reasoning_config": {}, "features": { "reasoning_config": {}, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "allenai/molmo-2-8b:free", "model_variant_permaslug": "allenai/molmo-2-8b-20260109:free", "adapter_name": "ParasailAdapter", "provider_name": "Parasail", "provider_info": { "name": "Parasail", "displayName": "Parasail", "slug": "parasail", "baseUrl": "https://api.parasail.io/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.parasail.io/legal/terms", "privacyPolicyURL": "https://www.parasail.io/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P5Ca01in28Ek1oxb5OtfZdEjQ", "user_37qaJKhqfUEFgVF46sarwDHxE50" ], "adapterName": "ParasailAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256" }, "ignoredProviderModels": [ "parasail-olmo-2-1124-7b-instruct", "parasail-qwen3-omni-30b-a3b-thinking", "parasail-qwen3-omni-30b-a3b-instruct", "parasail-dots-ocr", "parasail-auto-glm-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Parasail", "provider_slug": "parasail/bf16", "provider_model_id": "parasail-molmo2-8b", "quantization": "bf16", "variant": "free", "is_free": true, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 36864, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "frequency_penalty", "presence_penalty", "repetition_penalty", "seed", "stop", "top_k", "logit_bias", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.parasail.io/legal/terms", "privacyPolicyURL": "https://www.parasail.io/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0", "openai:completion_tokens": "0" }, "pricing_version_id": "cba2167e-8a12-41bb-9d8e-a39abd4907cc", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "bytedance-seed/seedream-4.5", "hf_slug": "", "updated_at": "2025-12-23T20:23:30.403+00:00", "created_at": "2025-12-23T19:51:46+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seedream 4.5", "short_name": "Seedream 4.5", "author": "bytedance-seed", "description": "Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details, lighting, and color tone. It also enhances portrait refinement and small-text rendering. The model’s multi-image composition capabilities have been significantly strengthened, and both reasoning performance and visual aesthetics continue to advance, enabling more accurate and artistically expressive image generation.\n\nPricing is $0.04 per output image, regardless of size.", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "image", "text" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seedream-4.5-20251203", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "2bc65671-3e31-4205-add1-10884b5cda4e", "name": "Seed | bytedance-seed/seedream-4.5-20251203", "context_length": 4096, "model": { "slug": "bytedance-seed/seedream-4.5", "hf_slug": "", "updated_at": "2025-12-23T20:23:30.403+00:00", "created_at": "2025-12-23T19:51:46+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seedream 4.5", "short_name": "Seedream 4.5", "author": "bytedance-seed", "description": "Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details, lighting, and color tone. It also enhances portrait refinement and small-text rendering. The model’s multi-image composition capabilities have been significantly strengthened, and both reasoning performance and visual aesthetics continue to advance, enabling more accurate and artistically expressive image generation.\n\nPricing is $0.04 per output image, regardless of size.", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "image", "text" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seedream-4.5-20251203", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "bytedance-seed/seedream-4.5", "model_variant_permaslug": "bytedance-seed/seedream-4.5-20251203", "adapter_name": "SeedreamAdapter", "provider_name": "Seed", "provider_info": { "name": "Seed", "displayName": "Seed", "slug": "seed", "baseUrl": "https://ark.ap-southeast.bytepluses.com/api/v3", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "SeedreamAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256" }, "ignoredProviderModels": [ "ep-20251223020539-6m7wz" ], "sendClientIp": false, "pricingStrategy": "seedream" }, "provider_display_name": "Seed", "provider_slug": "seed", "provider_model_id": "ep-20251223020539-6m7wz", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "frequency_penalty", "max_tokens", "temperature", "top_p" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_output": "0.04", "discount": 0 }, "variable_pricings": [], "pricing_json": { "seedream:cents_per_image_output": 4, "seedream:informational_output_tokens": "0" }, "pricing_version_id": "1aa3d4ce-6b6a-4cba-9585-5409c3359caf", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "bytedance-seed/seed-1.6-flash", "hf_slug": "", "updated_at": "2025-12-23T15:50:11.246001+00:00", "created_at": "2025-12-23T15:50:11+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seed 1.6 Flash", "short_name": "Seed 1.6 Flash", "author": "bytedance-seed", "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seed-1.6-flash-20250625", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "e01a1227-001b-44d4-a376-90850668fa84", "name": "Seed | bytedance-seed/seed-1.6-flash-20250625", "context_length": 262144, "model": { "slug": "bytedance-seed/seed-1.6-flash", "hf_slug": "", "updated_at": "2025-12-23T15:50:11.246001+00:00", "created_at": "2025-12-23T15:50:11+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seed 1.6 Flash", "short_name": "Seed 1.6 Flash", "author": "bytedance-seed", "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seed-1.6-flash-20250625", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "bytedance-seed/seed-1.6-flash", "model_variant_permaslug": "bytedance-seed/seed-1.6-flash-20250625", "adapter_name": "BytePlusAdapter", "provider_name": "Seed", "provider_info": { "name": "Seed", "displayName": "Seed", "slug": "seed", "baseUrl": "https://ark.ap-southeast.bytepluses.com/api/v3", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "BytePlusAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256" }, "ignoredProviderModels": [ "ep-20251223020539-6m7wz" ], "sendClientIp": false, "pricingStrategy": "byteplus" }, "provider_display_name": "Seed", "provider_slug": "seed/fp8", "provider_model_id": "ep-20251022091553-b9gf5", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "frequency_penalty", "max_tokens", "temperature", "top_p", "stop", "tools", "tool_choice", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "pricing": { "prompt": "0.000000075", "completion": "0.0000003", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 128000, "prompt": "0.0000001", "completions": "0.0000008", "input_cache_read": "0", "input_cache_write": "0" } ], "pricing_json": { "openai:prompt_tokens": 7.5e-8, "byteplus:prompt_tokens": "0.000000075", "openai:completion_tokens": 3e-7, "byteplus:completion_tokens": "0.0000003", "byteplus:long_context_threshold": "128000", "byteplus:prompt_tokens_long_context": "0.0000001", "byteplus:completion_tokens_long_context": "0.0000008" }, "pricing_version_id": "d70609e1-9841-4111-8962-b9967c58b5bb", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "bytedance-seed/seed-1.6", "hf_slug": "", "updated_at": "2025-12-23T15:49:57.589744+00:00", "created_at": "2025-12-23T15:49:57+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seed 1.6", "short_name": "Seed 1.6", "author": "bytedance-seed", "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seed-1.6-20250625", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d85c3862-4e0d-4f8d-955b-babc62f98124", "name": "Seed | bytedance-seed/seed-1.6-20250625", "context_length": 262144, "model": { "slug": "bytedance-seed/seed-1.6", "hf_slug": "", "updated_at": "2025-12-23T15:49:57.589744+00:00", "created_at": "2025-12-23T15:49:57+00:00", "hf_updated_at": null, "name": "ByteDance Seed: Seed 1.6", "short_name": "Seed 1.6", "author": "bytedance-seed", "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "bytedance-seed/seed-1.6-20250625", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "bytedance-seed/seed-1.6", "model_variant_permaslug": "bytedance-seed/seed-1.6-20250625", "adapter_name": "BytePlusAdapter", "provider_name": "Seed", "provider_info": { "name": "Seed", "displayName": "Seed", "slug": "seed", "baseUrl": "https://ark.ap-southeast.bytepluses.com/api/v3", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "BytePlusAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256" }, "ignoredProviderModels": [ "ep-20251223020539-6m7wz" ], "sendClientIp": false, "pricingStrategy": "byteplus" }, "provider_display_name": "Seed", "provider_slug": "seed/fp8", "provider_model_id": "ep-20251022091355-w7xt5", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "frequency_penalty", "max_tokens", "temperature", "top_p", "stop", "tools", "tool_choice", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.byteplus.com/en/docs/legal/docs-terms-of-service", "privacyPolicyURL": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy" }, "pricing": { "prompt": "0.00000025", "completion": "0.000002", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 128000, "prompt": "0.0000005", "completions": "0.000004", "input_cache_read": "0", "input_cache_write": "0" } ], "pricing_json": { "openai:prompt_tokens": 2.5e-7, "byteplus:prompt_tokens": "0.00000025", "openai:completion_tokens": 0.000002, "byteplus:completion_tokens": "0.000002", "byteplus:long_context_threshold": "128000", "byteplus:prompt_tokens_long_context": "0.0000005", "byteplus:completion_tokens_long_context": "0.000004" }, "pricing_version_id": "2d6fe62d-b1bd-49e8-a789-9612754d14b7", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-3-flash-preview", "hf_slug": "", "updated_at": "2025-12-17T16:17:44.159277+00:00", "created_at": "2025-12-17T15:57:58+00:00", "hf_updated_at": null, "name": "Google: Gemini 3 Flash Preview", "short_name": "Gemini 3 Flash Preview", "author": "google", "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "google/gemini-3-flash-preview-20251217", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "low", "medium", "high", "minimal" ], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "low", "medium", "high", "minimal" ], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "google-ai-studio" ], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d06bdb18-3cc2-46b0-bf23-922e485dc255", "name": "Google | google/gemini-3-flash-preview-20251217", "context_length": 1048576, "model": { "slug": "google/gemini-3-flash-preview", "hf_slug": "", "updated_at": "2025-12-17T16:17:44.159277+00:00", "created_at": "2025-12-17T15:57:58+00:00", "hf_updated_at": null, "name": "Google: Gemini 3 Flash Preview", "short_name": "Gemini 3 Flash Preview", "author": "google", "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "google/gemini-3-flash-preview-20251217", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "low", "medium", "high", "minimal" ], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "low", "medium", "high", "minimal" ], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "google-ai-studio" ], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-3-flash-preview", "model_variant_permaslug": "google/gemini-3-flash-preview-20251217", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-3-flash-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "seed", "response_format", "stop", "structured_outputs", "tool_choice", "tools" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000005", "completion": "0.000003", "image": "0.0000005", "audio": "0.000001", "input_audio_cache": "0.0000001", "input_cache_read": "0.00000005", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.000003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 5e-7, "gemini:reasoning_tokens": 0.000003, "gemini:cache_read_tokens": 5e-8, "gemini:completion_tokens": 0.000003, "gemini:text_input_tokens": 5e-7, "gemini:audio_input_tokens": 0.000001, "gemini:image_input_tokens": 5e-7, "gemini:video_input_tokens": 5e-7, "gemini:cache_read_text_tokens": 5e-8, "gemini:cache_read_audio_tokens": 1e-7, "gemini:cache_read_image_tokens": 5e-8, "gemini:cache_read_video_tokens": 5e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 1e-7, "gemini:cache_read_text_tokens_high_context": 1e-7, "gemini:cache_read_audio_tokens_high_context": 2e-7, "gemini:cache_read_image_tokens_high_context": 1e-7, "gemini:cache_read_video_tokens_high_context": 1e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "74036019-cef5-428a-b27f-0519ac4e5720", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "black-forest-labs/flux.2-max", "hf_slug": "", "updated_at": "2025-12-16T17:17:13.934433+00:00", "created_at": "2025-12-16T03:59:30.221034+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Max", "short_name": "FLUX.2 Max", "author": "black-forest-labs", "description": "FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nInput: We charge $0.03 for each megapixel on the input (i.e. reference images for editing)\nOutput: The first generated megapixel is charged $0.07. Each subsequent megapixel is charged $0.03.", "model_version_group_id": null, "context_length": 46864, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "black-forest-labs/flux.2-max", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "79c839a0-5da8-4cc4-8324-dab2dd6893b0", "name": "Black Forest Labs | black-forest-labs/flux.2-max", "context_length": 46864, "model": { "slug": "black-forest-labs/flux.2-max", "hf_slug": "", "updated_at": "2025-12-16T17:17:13.934433+00:00", "created_at": "2025-12-16T03:59:30.221034+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Max", "short_name": "FLUX.2 Max", "author": "black-forest-labs", "description": "FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nInput: We charge $0.03 for each megapixel on the input (i.e. reference images for editing)\nOutput: The first generated megapixel is charged $0.07. Each subsequent megapixel is charged $0.03.", "model_version_group_id": null, "context_length": 46864, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "black-forest-labs/flux.2-max", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": null, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "black-forest-labs/flux.2-max", "model_variant_permaslug": "black-forest-labs/flux.2-max", "adapter_name": "BlackForestLabsAdapter", "provider_name": "Black Forest Labs", "provider_info": { "name": "Black Forest Labs", "displayName": "Black Forest Labs", "slug": "black-forest-labs", "baseUrl": "https://api.us3.bfl.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "BlackForestLabsAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://bfl.ai&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "bfl" }, "provider_display_name": "Black Forest Labs", "provider_slug": "black-forest-labs", "provider_model_id": "flux-2-max", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "seed" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_output": "0.00001708984375", "discount": 0 }, "variable_pricings": [], "pricing_json": { "bfl:upstream_cost_cents": "1", "bfl:informational_output_megapixels": 0.07 }, "pricing_version_id": "56413436-161e-411a-852e-d10df3fb508b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.2-chat", "hf_slug": "", "updated_at": "2025-12-11T18:20:07.580251+00:00", "created_at": "2025-12-10T18:03:03.398082+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2 Chat", "short_name": "GPT-5.2 Chat", "author": "openai", "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-chat-20251211", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "e510ac71-5b26-4f05-b214-f95ba530d45d", "name": "OpenAI | openai/gpt-5.2-chat-20251211", "context_length": 128000, "model": { "slug": "openai/gpt-5.2-chat", "hf_slug": "", "updated_at": "2025-12-11T18:20:07.580251+00:00", "created_at": "2025-12-10T18:03:03.398082+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2 Chat", "short_name": "GPT-5.2 Chat", "author": "openai", "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-chat-20251211", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.2-chat", "model_variant_permaslug": "openai/gpt-5.2-chat-20251211", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.2-chat-latest", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000175", "completion": "0.000014", "input_cache_read": "0.000000175", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000175, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000014, "openai_responses:cached_prompt_tokens": 1.75e-7 }, "pricing_version_id": "8b5b51b9-4341-46e1-a5aa-7dd5ffa66a3f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.2-pro", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-12-10T18:03:00.055991+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2 Pro", "short_name": "GPT-5.2 Pro", "author": "openai", "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-pro-20251211", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "medium", "high", "xhigh" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "medium", "high", "xhigh" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "1abae580-6f7a-4092-ae6c-b87ce6067f61", "name": "OpenAI | openai/gpt-5.2-pro-20251211", "context_length": 400000, "model": { "slug": "openai/gpt-5.2-pro", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-12-10T18:03:00.055991+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2 Pro", "short_name": "GPT-5.2 Pro", "author": "openai", "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-pro-20251211", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "medium", "high", "xhigh" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "medium", "high", "xhigh" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.2-pro", "model_variant_permaslug": "openai/gpt-5.2-pro-20251211", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.2-pro-2025-12-11", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000021", "completion": "0.000168", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.000021, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000168 }, "pricing_version_id": "28cb6295-41bb-4331-80fc-0126e243b777", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.2", "hf_slug": "", "updated_at": "2025-12-11T18:20:09.990885+00:00", "created_at": "2025-12-10T18:02:55.765028+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2", "short_name": "GPT-5.2", "author": "openai", "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-20251211", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f00142c2-6a93-49ce-9e36-5593b904ce3b", "name": "OpenAI | openai/gpt-5.2-20251211", "context_length": 400000, "model": { "slug": "openai/gpt-5.2", "hf_slug": "", "updated_at": "2025-12-11T18:20:09.990885+00:00", "created_at": "2025-12-10T18:02:55.765028+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.2", "short_name": "GPT-5.2", "author": "openai", "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.2-20251211", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.2", "model_variant_permaslug": "openai/gpt-5.2-20251211", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.2-2025-12-11", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000175", "completion": "0.000014", "input_cache_read": "0.000000175", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000175, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000014, "openai_responses:cached_prompt_tokens": 1.75e-7 }, "pricing_version_id": "cbf3dc18-db59-46fa-9a74-127ca74f3ab7", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "is_mandatory_reasoning": false, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "sourceful/riverflow-v2-max-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:09.632974+00:00", "created_at": "2025-12-08T23:50:49+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Max Preview", "short_name": "Riverflow V2 Max Preview", "author": "sourceful", "description": "Riverflow V2 Max Preview is the most powerful variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.075 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-max-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "8db3f8c4-038a-41ba-924a-e5cf268ee330", "name": "Sourceful | sourceful/riverflow-v2-max-preview", "context_length": 8192, "model": { "slug": "sourceful/riverflow-v2-max-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:09.632974+00:00", "created_at": "2025-12-08T23:50:49+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Max Preview", "short_name": "Riverflow V2 Max Preview", "author": "sourceful", "description": "Riverflow V2 Max Preview is the most powerful variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.075 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-max-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "sourceful/riverflow-v2-max-preview", "model_variant_permaslug": "sourceful/riverflow-v2-max-preview", "adapter_name": "SourcefulAdapter", "provider_name": "Sourceful", "provider_info": { "name": "Sourceful", "displayName": "Sourceful", "slug": "sourceful", "baseUrl": "https://design-api.sourceful.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "SourcefulAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.sourceful.com&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "sourceful" }, "provider_display_name": "Sourceful", "provider_slug": "sourceful", "provider_model_id": "sourceful/riverflow-v2-max-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_token": "0.00001796407185628743", "image_output": "0.075", "discount": 0 }, "variable_pricings": [], "pricing_json": { "sourceful:cents_per_image_output": 7.5 }, "pricing_version_id": "a1b54c23-6587-47bb-b0f5-ccd18f46481f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "sourceful/riverflow-v2-standard-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:12.112144+00:00", "created_at": "2025-12-08T23:50:36+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Standard Preview", "short_name": "Riverflow V2 Standard Preview", "author": "sourceful", "description": "Riverflow V2 Standard Preview is the standard variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.035 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-standard-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "69bbbbea-d1e2-47ed-8d2a-ee2e9a329005", "name": "Sourceful | sourceful/riverflow-v2-standard-preview", "context_length": 8192, "model": { "slug": "sourceful/riverflow-v2-standard-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:12.112144+00:00", "created_at": "2025-12-08T23:50:36+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Standard Preview", "short_name": "Riverflow V2 Standard Preview", "author": "sourceful", "description": "Riverflow V2 Standard Preview is the standard variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.035 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-standard-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "sourceful/riverflow-v2-standard-preview", "model_variant_permaslug": "sourceful/riverflow-v2-standard-preview", "adapter_name": "SourcefulAdapter", "provider_name": "Sourceful", "provider_info": { "name": "Sourceful", "displayName": "Sourceful", "slug": "sourceful", "baseUrl": "https://design-api.sourceful.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "SourcefulAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.sourceful.com&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "sourceful" }, "provider_display_name": "Sourceful", "provider_slug": "sourceful", "provider_model_id": "sourceful/riverflow-v2-standard-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_token": "0.00000838323353293413", "image_output": "0.035", "discount": 0 }, "variable_pricings": [], "pricing_json": { "sourceful:cents_per_image_output": 3.5 }, "pricing_version_id": "1172ed9d-3508-4dd6-a1da-8e463dede88e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "sourceful/riverflow-v2-fast-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:14.431363+00:00", "created_at": "2025-12-08T23:50:20+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Fast Preview", "short_name": "Riverflow V2 Fast Preview", "author": "sourceful", "description": "Riverflow V2 Fast Preview is the fastest variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.03 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-fast-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ee33a0ab-9f6a-4121-aa4a-56d4b3fe630f", "name": "Sourceful | sourceful/riverflow-v2-fast-preview", "context_length": 8192, "model": { "slug": "sourceful/riverflow-v2-fast-preview", "hf_slug": "", "updated_at": "2025-12-09T14:33:14.431363+00:00", "created_at": "2025-12-08T23:50:20+00:00", "hf_updated_at": null, "name": "Sourceful: Riverflow V2 Fast Preview", "short_name": "Riverflow V2 Fast Preview", "author": "sourceful", "description": "Riverflow V2 Fast Preview is the fastest variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image and image-to-image model family.\n\nPricing is $0.03 per output image, regardless of size.\n\nSourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "sourceful/riverflow-v2-fast-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "sourceful/riverflow-v2-fast-preview", "model_variant_permaslug": "sourceful/riverflow-v2-fast-preview", "adapter_name": "SourcefulAdapter", "provider_name": "Sourceful", "provider_info": { "name": "Sourceful", "displayName": "Sourceful", "slug": "sourceful", "baseUrl": "https://design-api.sourceful.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "SourcefulAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.sourceful.com&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "sourceful" }, "provider_display_name": "Sourceful", "provider_slug": "sourceful", "provider_model_id": "sourceful/riverflow-v2-fast-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.sourceful.com/legal/spring-terms-of-use", "privacyPolicyURL": "https://www.sourceful.com/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_token": "0.00000718562874251497", "image_output": "0.03", "discount": 0 }, "variable_pricings": [], "pricing_json": { "sourceful:cents_per_image_output": 3 }, "pricing_version_id": "0ebeb00e-efd5-4be3-93cf-7f57eb03eedb", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "z-ai/glm-4.6v", "hf_slug": "zai-org/GLM-4.6V", "updated_at": "2025-12-08T15:45:24.970322+00:00", "created_at": "2025-12-08T15:24:22.464154+00:00", "hf_updated_at": null, "name": "Z.AI: GLM 4.6V", "short_name": "GLM 4.6V", "author": "z-ai", "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "z-ai/glm-4.6-20251208", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.8, "top_p": 0.6, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "a341c9a0-4b18-429a-b620-9e4fd811803c", "name": "SiliconFlow | z-ai/glm-4.6-20251208", "context_length": 131072, "model": { "slug": "z-ai/glm-4.6v", "hf_slug": "zai-org/GLM-4.6V", "updated_at": "2025-12-08T15:45:24.970322+00:00", "created_at": "2025-12-08T15:24:22.464154+00:00", "hf_updated_at": null, "name": "Z.AI: GLM 4.6V", "short_name": "GLM 4.6V", "author": "z-ai", "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "z-ai/glm-4.6-20251208", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.8, "top_p": 0.6, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "z-ai/glm-4.6v", "model_variant_permaslug": "z-ai/glm-4.6-20251208", "adapter_name": "SiliconFlowAdapter", "provider_name": "SiliconFlow", "provider_info": { "name": "SiliconFlow", "displayName": "SiliconFlow", "slug": "siliconflow", "baseUrl": "https://api.siliconflow.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "SiliconFlowAdapter", "isMultipartSupported": false, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "/images/icons/SiliconFlow.svg" }, "ignoredProviderModels": [ "inclusionAI/Ling-mini-2.0", "inclusionAI/Ring-flash-2.0", "inclusionAI/Ling-flash-2.0" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "SiliconFlow", "provider_slug": "siliconflow/fp8", "provider_model_id": "zai-org/GLM-4.6V", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 131072, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "temperature", "top_p", "top_k", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "pricing": { "prompt": "0.0000003", "completion": "0.0000009", "image": "0", "request": "0", "input_cache_read": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000003", "openai:completion_tokens": "0.0000009" }, "pricing_version_id": "12be62ec-1783-4c33-a291-7b82056a75df", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_base64_video_input": false, "supports_video_urls": false, "supports_tool_choice": { "literal_none": false, "literal_auto": true, "literal_required": false, "type_function": false } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.1-codex-max", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-12-04T20:08:54.10013+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex-Max", "short_name": "GPT-5.1-Codex-Max", "author": "openai", "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. \nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. ", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.1-codex-max-20251204", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f225ad30-4cb3-4e28-b677-0eff326af277", "name": "OpenAI | openai/gpt-5.1-codex-max-20251204", "context_length": 400000, "model": { "slug": "openai/gpt-5.1-codex-max", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-12-04T20:08:54.10013+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex-Max", "short_name": "GPT-5.1-Codex-Max", "author": "openai", "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. \nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. ", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "openai/gpt-5.1-codex-max-20251204", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.1-codex-max", "model_variant_permaslug": "openai/gpt-5.1-codex-max-20251204", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.1-codex-max", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "seed", "max_tokens", "response_format", "structured_outputs", "tool_choice", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "caa166de-dce5-44c0-a280-fef824e3d18e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "amazon/nova-2-lite-v1", "hf_slug": "", "updated_at": "2025-12-05T00:11:57.060181+00:00", "created_at": "2025-12-02T17:31:12+00:00", "hf_updated_at": null, "name": "Amazon: Nova 2 Lite", "short_name": "Nova 2 Lite", "author": "amazon", "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. \n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image", "video", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "amazon/nova-2-lite-v1", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "b1b489e5-7029-4ab2-9e12-5415b55b4afa", "name": "Amazon Bedrock | amazon/nova-2-lite-v1", "context_length": 1000000, "model": { "slug": "amazon/nova-2-lite-v1", "hf_slug": "", "updated_at": "2025-12-05T00:11:57.060181+00:00", "created_at": "2025-12-02T17:31:12+00:00", "hf_updated_at": null, "name": "Amazon: Nova 2 Lite", "short_name": "Nova 2 Lite", "author": "amazon", "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. \n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image", "video", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "amazon/nova-2-lite-v1", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "amazon/nova-2-lite-v1", "model_variant_permaslug": "amazon/nova-2-lite-v1", "adapter_name": "AmazonBedrockConverseNovaReasoningAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseNovaReasoningAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.amazon.nova-2-lite-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "stop", "tool_choice", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.0000003", "completion": "0.0000025", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": false, "supports_base64_video_input": true, "supports_video_urls": false, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "is_mandatory_reasoning": false, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/ministral-14b-2512", "hf_slug": "mistralai/Ministral-3-14B-Instruct-2512", "updated_at": "2025-12-10T16:54:21.432818+00:00", "created_at": "2025-12-02T13:22:15.851192+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 14B 2512", "short_name": "Ministral 3 14B 2512", "author": "mistralai", "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-14b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "0b53717b-9af5-4de3-80af-ebedd2adf981", "name": "Mistral | mistralai/ministral-14b-2512", "context_length": 262144, "model": { "slug": "mistralai/ministral-14b-2512", "hf_slug": "mistralai/Ministral-3-14B-Instruct-2512", "updated_at": "2025-12-10T16:54:21.432818+00:00", "created_at": "2025-12-02T13:22:15.851192+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 14B 2512", "short_name": "Ministral 3 14B 2512", "author": "mistralai", "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-14b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/ministral-14b-2512", "model_variant_permaslug": "mistralai/ministral-14b-2512", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "ministral-14b-2512", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.0000002", "completion": "0.0000002", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 2e-7, "mistral:completion_tokens": 2e-7 }, "pricing_version_id": "b0ff8ca8-ffa3-4feb-ad65-91090aa5c22b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/ministral-8b-2512", "hf_slug": "mistralai/Ministral-3-8B-Instruct-2512", "updated_at": "2025-12-10T16:54:03.715606+00:00", "created_at": "2025-12-02T13:20:54.103183+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 8B 2512", "short_name": "Ministral 3 8B 2512", "author": "mistralai", "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-8b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "c85d26e1-1e0c-449b-9775-2afce7ae510b", "name": "Mistral | mistralai/ministral-8b-2512", "context_length": 262144, "model": { "slug": "mistralai/ministral-8b-2512", "hf_slug": "mistralai/Ministral-3-8B-Instruct-2512", "updated_at": "2025-12-10T16:54:03.715606+00:00", "created_at": "2025-12-02T13:20:54.103183+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 8B 2512", "short_name": "Ministral 3 8B 2512", "author": "mistralai", "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-8b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/ministral-8b-2512", "model_variant_permaslug": "mistralai/ministral-8b-2512", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "ministral-8b-2512", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.00000015", "completion": "0.00000015", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 1.5e-7, "mistral:completion_tokens": 1.5e-7 }, "pricing_version_id": "d683019f-fb1b-407c-9fef-5b0efff712e1", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/ministral-3b-2512", "hf_slug": "mistralai/Ministral-3-3B-Instruct-2512", "updated_at": "2025-12-10T16:53:53.577361+00:00", "created_at": "2025-12-02T13:19:20.726635+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 3B 2512", "short_name": "Ministral 3 3B 2512", "author": "mistralai", "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-3b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "b9f6828f-aef9-498a-91f5-6816fbf72420", "name": "Mistral | mistralai/ministral-3b-2512", "context_length": 131072, "model": { "slug": "mistralai/ministral-3b-2512", "hf_slug": "mistralai/Ministral-3-3B-Instruct-2512", "updated_at": "2025-12-10T16:53:53.577361+00:00", "created_at": "2025-12-02T13:19:20.726635+00:00", "hf_updated_at": null, "name": "Mistral: Ministral 3 3B 2512", "short_name": "Ministral 3 3B 2512", "author": "mistralai", "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/ministral-3b-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.3, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/ministral-3b-2512", "model_variant_permaslug": "mistralai/ministral-3b-2512", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "ministral-3b-2512", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tool_choice", "tools" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.0000001", "completion": "0.0000001", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 1e-7, "mistral:completion_tokens": 1e-7 }, "pricing_version_id": "ec8022e6-9795-4d78-a729-b7c198e0326d", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-large-2512", "hf_slug": "", "updated_at": "2025-12-02T15:19:24.969824+00:00", "created_at": "2025-12-01T21:27:52.65109+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Large 3 2512", "short_name": "Mistral Large 3 2512", "author": "mistralai", "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/mistral-large-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.0645, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "text", "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "fa718841-07ea-4b7e-b8a3-6069545c7e6a", "name": "Mistral | mistralai/mistral-large-2512", "context_length": 262144, "model": { "slug": "mistralai/mistral-large-2512", "hf_slug": "", "updated_at": "2025-12-02T15:19:24.969824+00:00", "created_at": "2025-12-01T21:27:52.65109+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Large 3 2512", "short_name": "Mistral Large 3 2512", "author": "mistralai", "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "", "permaslug": "mistralai/mistral-large-2512", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.0645, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "text", "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-large-2512", "model_variant_permaslug": "mistralai/mistral-large-2512", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "mistral-large-2512", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.0000005", "completion": "0.0000015", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 5e-7, "mistral:completion_tokens": 0.0000015 }, "pricing_version_id": "063c942f-5035-4cfc-8b26-911b375a5c4a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": false, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "black-forest-labs/flux.2-flex", "hf_slug": "", "updated_at": "2025-11-25T16:34:07.604557+00:00", "created_at": "2025-11-25T04:46:27.810953+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Flex", "short_name": "FLUX.2 Flex", "author": "black-forest-labs", "description": "FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nWe charge $0.06 for each megapixel on both input and output side.", "model_version_group_id": null, "context_length": 67344, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "black-forest-labs/flux.2-flex", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ec92e60a-e4f4-474e-b1aa-7b48a509b343", "name": "Black Forest Labs | black-forest-labs/flux.2-flex", "context_length": 67344, "model": { "slug": "black-forest-labs/flux.2-flex", "hf_slug": "", "updated_at": "2025-11-25T16:34:07.604557+00:00", "created_at": "2025-11-25T04:46:27.810953+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Flex", "short_name": "FLUX.2 Flex", "author": "black-forest-labs", "description": "FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nWe charge $0.06 for each megapixel on both input and output side.", "model_version_group_id": null, "context_length": 67344, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "black-forest-labs/flux.2-flex", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "black-forest-labs/flux.2-flex", "model_variant_permaslug": "black-forest-labs/flux.2-flex", "adapter_name": "BlackForestLabsAdapter", "provider_name": "Black Forest Labs", "provider_info": { "name": "Black Forest Labs", "displayName": "Black Forest Labs", "slug": "black-forest-labs", "baseUrl": "https://api.us3.bfl.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "BlackForestLabsAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://bfl.ai&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "bfl" }, "provider_display_name": "Black Forest Labs", "provider_slug": "black-forest-labs", "provider_model_id": "flux-2-flex", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "seed" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_token": "0.0000146484375", "image_output": "0.0000146484375", "discount": 0 }, "variable_pricings": [], "pricing_json": { "bfl:upstream_cost_cents": "1", "bfl:informational_input_megapixels": 0.06, "bfl:informational_output_megapixels": 0.06 }, "pricing_version_id": "9fbdc6b3-1cfc-40a8-ad76-5f6cf1c6a31c", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "black-forest-labs/flux.2-pro", "hf_slug": "", "updated_at": "2025-11-25T16:34:12.266076+00:00", "created_at": "2025-11-25T00:24:34.639016+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Pro", "short_name": "FLUX.2 Pro", "author": "black-forest-labs", "description": "A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs. Designed for production workloads, it balances speed and quality while supporting text-to-image and image editing up to 4 MP resolution.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nInput: We charge $0.015 for each megapixel on the input (i.e. reference images for editing)\nOutput: The first megapixel is charged $0.03 and then each subsequent MP will be charged $0.015. ", "model_version_group_id": null, "context_length": 46864, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "black-forest-labs/flux.2-pro", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "660ad218-5dae-4429-83fa-528514aa9bb8", "name": "Black Forest Labs | black-forest-labs/flux.2-pro", "context_length": 46864, "model": { "slug": "black-forest-labs/flux.2-pro", "hf_slug": "", "updated_at": "2025-11-25T16:34:12.266076+00:00", "created_at": "2025-11-25T00:24:34.639016+00:00", "hf_updated_at": null, "name": "Black Forest Labs: FLUX.2 Pro", "short_name": "FLUX.2 Pro", "author": "black-forest-labs", "description": "A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs. Designed for production workloads, it balances speed and quality while supporting text-to-image and image editing up to 4 MP resolution.\n\nPricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2):\nInput: We charge $0.015 for each megapixel on the input (i.e. reference images for editing)\nOutput: The first megapixel is charged $0.03 and then each subsequent MP will be charged $0.015. ", "model_version_group_id": null, "context_length": 46864, "input_modalities": [ "text", "image" ], "output_modalities": [ "image" ], "has_text_output": false, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "black-forest-labs/flux.2-pro", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "black-forest-labs/flux.2-pro", "model_variant_permaslug": "black-forest-labs/flux.2-pro", "adapter_name": "BlackForestLabsAdapter", "provider_name": "Black Forest Labs", "provider_info": { "name": "Black Forest Labs", "displayName": "Black Forest Labs", "slug": "black-forest-labs", "baseUrl": "https://api.bfl.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "BlackForestLabsAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://bfl.ai&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "bfl" }, "provider_display_name": "Black Forest Labs", "provider_slug": "black-forest-labs", "provider_model_id": "flux-2-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "seed" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://bfl.ai/legal/terms-of-service", "privacyPolicyURL": "https://bfl.ai/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "image_output": "0.00000732421875", "discount": 0 }, "variable_pricings": [], "pricing_json": { "bfl:upstream_cost_cents": "1", "bfl:informational_output_megapixels": 0.03 }, "pricing_version_id": "e091d2ff-e677-4f80-8303-6c2485098a3f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-opus-4.5", "hf_slug": "", "updated_at": "2026-01-15T17:57:03.680811+00:00", "created_at": "2025-11-24T18:56:20+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4.5", "short_name": "Claude Opus 4.5", "author": "anthropic", "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-opus-20251124", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "be883404-eb42-4b2d-b6e4-c7daa3aa8d62", "name": "Anthropic | anthropic/claude-4.5-opus-20251124", "context_length": 200000, "model": { "slug": "anthropic/claude-opus-4.5", "hf_slug": "", "updated_at": "2026-01-15T17:57:03.680811+00:00", "created_at": "2025-11-24T18:56:20+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4.5", "short_name": "Claude Opus 4.5", "author": "anthropic", "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-opus-20251124", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-opus-4.5", "model_variant_permaslug": "anthropic/claude-4.5-opus-20251124", "adapter_name": "AnthropicMessageAdapter", "provider_name": "Anthropic", "provider_info": { "name": "Anthropic", "displayName": "Anthropic", "slug": "anthropic", "baseUrl": "https://api.anthropic.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.anthropic.com/legal/commercial-terms", "privacyPolicyURL": "https://www.anthropic.com/legal/privacy", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AnthropicMessageAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.anthropic.com/", "byokEnabled": true, "icon": { "url": "/images/icons/Anthropic.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Anthropic", "provider_slug": "anthropic", "provider_model_id": "claude-opus-4-5-20251101", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "stop", "reasoning", "include_reasoning", "tool_choice", "tools", "structured_outputs", "response_format", "verbosity" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.anthropic.com/legal/commercial-terms", "privacyPolicyURL": "https://www.anthropic.com/legal/privacy", "requiresUserIDs": true }, "pricing": { "prompt": "0.000005", "completion": "0.000025", "input_cache_read": "0.0000005", "input_cache_write": "0.00000625", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000005, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 5e-7, "anthropic:completion_tokens": 0.000025, "anthropic:cache_write_1h_tokens": 0.00001, "anthropic:cache_write_5m_tokens": 0.00000625 }, "pricing_version_id": "2b155b3b-876e-446f-98ca-ad47df5dffce", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": 40, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-3-pro-image-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-20T15:49:57.064095+00:00", "hf_updated_at": null, "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "short_name": "Nano Banana Pro (Gemini 3 Pro Image Preview)", "author": "google", "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-3-pro-image-preview-20251120", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": false, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": false, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f5a725e2-8f66-4754-9232-7550685ab3d0", "name": "Google AI Studio | google/gemini-3-pro-image-preview-20251120", "context_length": 65536, "model": { "slug": "google/gemini-3-pro-image-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-20T15:49:57.064095+00:00", "hf_updated_at": null, "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "short_name": "Nano Banana Pro (Gemini 3 Pro Image Preview)", "author": "google", "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-3-pro-image-preview-20251120", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": false, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": false, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-3-pro-image-preview", "model_variant_permaslug": "google/gemini-3-pro-image-preview-20251120", "adapter_name": "GoogleAIStudioGeminiAdapter", "provider_name": "Google AI Studio", "provider_info": { "name": "Google AI Studio", "displayName": "Google AI Studio", "slug": "google-ai-studio", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleAIStudioGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "/images/icons/GoogleAIStudio.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-1p", "gemini-2.5-pro-1p-recitation-off", "gemini-2.5-flash-1p", "gemini-2.5-flash-1p-recitation-off", "gemini-2.5-flash-lite-preview-06-11-summarized", "gemini-2.5-flash", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-1.5-pro-latest", "gemini-1.5-pro", "gemini-1.5-flash-latest", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-1.5-flash-8b-latest", "gemini-2.5-pro-preview-03-25", "gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-preview", "gemini-2.0-pro-exp", "gemini-2.0-flash-thinking-exp", "gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts", "learnlm-2.0-flash-experimental", "gracefulgolem", "gemini-2.5-flash-preview-05-20", "gemini-2.5-pro-preview-06-05", "gemini-2.0-flash-exp-image-generation", "gemini-2.0-flash-preview-image-generation", "gemini-2.0-flash-lite-preview-02-05", "gemini-2.0-pro-exp-02-05", "gemini-exp-1206", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-flash-thinking-exp-1219", "gemma-3-1b-it", "gemini-flash-latest", "gemini-flash-lite-latest", "gemini-pro-latest", "gemini-robotics-er-1.5-preview", "gemini-embedding-001", "riftrunner-fst-rewind", "gemini-3-pro-image-preview", "nano-banana-pro-preview", "fiercefalcon", "fiercefalcon-inline-citation", "fiercefalcon-blocked-sites" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google AI Studio", "provider_slug": "google-ai-studio", "provider_model_id": "gemini-3-pro-image-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "seed", "response_format", "stop", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "pricing": { "prompt": "0.000002", "completion": "0.000012", "image": "0.000002", "audio": "0.000002", "input_audio_cache": "0.0000002", "input_cache_read": "0.0000002", "input_cache_write": "0.000000375", "internal_reasoning": "0.000012", "image_output": "0.00012", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 0.000002, "gemini:reasoning_tokens": 0.000012, "gemini:cache_read_tokens": 2e-7, "gemini:completion_tokens": 0.000012, "gemini:text_input_tokens": 0.000002, "gemini:audio_input_tokens": 0.000002, "gemini:image_input_tokens": 0.000002, "gemini:video_input_tokens": 0.000002, "gemini:image_output_tokens": 0.00012, "gemini:cache_read_text_tokens": 2e-7, "gemini:cache_read_audio_tokens": 2e-7, "gemini:cache_read_image_tokens": 2e-7, "gemini:cache_read_video_tokens": 2e-7, "gemini:cache_write_storage_hours": 0.0000045, "gemini:prompt_tokens_high_context": 0.000004, "gemini:reasoning_tokens_high_context": 0.000018, "gemini:cache_read_tokens_high_context": 4e-7, "gemini:completion_tokens_high_context": 0.000018, "gemini:cache_read_text_tokens_high_context": 4e-7, "gemini:cache_read_audio_tokens_high_context": 4e-7, "gemini:cache_read_image_tokens_high_context": 4e-7, "gemini:cache_read_video_tokens_high_context": 4e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "4c53647d-b03e-43cf-a0eb-1ea158e4626f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": 250, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": "global", "deprecation_date": null } }, { "slug": "x-ai/grok-4.1-fast", "hf_slug": "", "updated_at": "2025-12-03T20:06:03.459371+00:00", "created_at": "2025-11-19T21:25:02.724692+00:00", "hf_updated_at": null, "name": "xAI: Grok 4.1 Fast", "short_name": "Grok 4.1 Fast", "author": "x-ai", "description": "Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "The free Grok 4.1 Fast period has ended. To continue using this model, please migrate to the paid slug: x-ai/grok-4.1-fast", "permaslug": "x-ai/grok-4.1-fast", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "9821aa0e-dce3-4c27-9716-161359123d0b", "name": "xAI | x-ai/grok-4.1-fast", "context_length": 2000000, "model": { "slug": "x-ai/grok-4.1-fast", "hf_slug": "", "updated_at": "2025-12-03T20:06:03.459371+00:00", "created_at": "2025-11-19T21:25:02.724692+00:00", "hf_updated_at": null, "name": "xAI: Grok 4.1 Fast", "short_name": "Grok 4.1 Fast", "author": "x-ai", "description": "Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "The free Grok 4.1 Fast period has ended. To continue using this model, please migrate to the paid slug: x-ai/grok-4.1-fast", "permaslug": "x-ai/grok-4.1-fast", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "x-ai/grok-4.1-fast", "model_variant_permaslug": "x-ai/grok-4.1-fast", "adapter_name": "XAIResponsesAdapter", "provider_name": "xAI", "provider_info": { "name": "xAI", "displayName": "xAI", "slug": "xai", "baseUrl": "https://api.x.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "XAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.x.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "xAI", "provider_slug": "xai", "provider_model_id": "grok-4-1-fast-non-reasoning", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 30000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "seed", "logprobs", "top_logprobs", "response_format", "tools", "tool_choice", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000002", "completion": "0.0000005", "image": "0", "request": "0", "input_cache_read": "0.00000005", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 128000, "prompt": "0.0000004", "completions": "0.000001", "input_cache_read": "0.00000005" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-3-pro-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-18T14:04:28+00:00", "hf_updated_at": null, "name": "Google: Gemini 3 Pro Preview", "short_name": "Gemini 3 Pro Preview", "author": "google", "description": "Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.\n\nBuilt for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-3-pro-preview-20251117", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high", "low" ], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high", "low" ], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ca4e1f52-1f15-4258-a4eb-d6b56c0c4057", "name": "Google | google/gemini-3-pro-preview-20251117", "context_length": 1048576, "model": { "slug": "google/gemini-3-pro-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-18T14:04:28+00:00", "hf_updated_at": null, "name": "Google: Gemini 3 Pro Preview", "short_name": "Gemini 3 Pro Preview", "author": "google", "description": "Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.\n\nBuilt for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-3-pro-preview-20251117", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high", "low" ], "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high", "low" ], "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-3-pro-preview", "model_variant_permaslug": "google/gemini-3-pro-preview-20251117", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-3-pro-preview", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65536, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000002", "completion": "0.000012", "image": "0.000002", "audio": "0.000002", "input_audio_cache": "0.0000002", "input_cache_read": "0.0000002", "input_cache_write": "0.000000375", "internal_reasoning": "0.000012", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.000004", "completions": "0.000018", "input_cache_read": "0.0000004", "input_cache_write": "0.00000075" } ], "pricing_json": { "gemini:prompt_tokens": 0.000002, "gemini:reasoning_tokens": 0.000012, "gemini:cache_read_tokens": 2e-7, "gemini:completion_tokens": 0.000012, "gemini:text_input_tokens": 0.000002, "gemini:audio_input_tokens": 0.000002, "gemini:image_input_tokens": 0.000002, "gemini:video_input_tokens": 0.000002, "gemini:cache_read_text_tokens": 2e-7, "gemini:cache_read_audio_tokens": 2e-7, "gemini:cache_read_image_tokens": 2e-7, "gemini:cache_read_video_tokens": 2e-7, "gemini:cache_write_storage_hours": 0.0000045, "gemini:prompt_tokens_high_context": 0.000004, "gemini:reasoning_tokens_high_context": 0.000018, "gemini:cache_read_tokens_high_context": 4e-7, "gemini:completion_tokens_high_context": 0.000018, "gemini:cache_read_text_tokens_high_context": 4e-7, "gemini:cache_read_audio_tokens_high_context": 4e-7, "gemini:cache_read_image_tokens_high_context": 4e-7, "gemini:cache_read_video_tokens_high_context": 4e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "3b180fff-70f2-4a89-9a66-9d051e7b9bf9", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "openai/gpt-5.1", "hf_slug": "", "updated_at": "2025-11-13T18:58:25.56227+00:00", "created_at": "2025-11-13T18:58:25+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1", "short_name": "GPT-5.1", "author": "openai", "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "764eb97f-8bab-4326-b29b-7a8799b00a70", "name": "OpenAI | openai/gpt-5.1-20251113", "context_length": 400000, "model": { "slug": "openai/gpt-5.1", "hf_slug": "", "updated_at": "2025-11-13T18:58:25.56227+00:00", "created_at": "2025-11-13T18:58:25+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1", "short_name": "GPT-5.1", "author": "openai", "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.1", "model_variant_permaslug": "openai/gpt-5.1-20251113", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai/default", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai/default", "provider_model_id": "gpt-5.1-2025-11-13", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "177855b5-4b6e-4f70-a823-4eb03aa1322b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": false, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.1-chat", "hf_slug": "", "updated_at": "2025-11-13T18:58:22.624591+00:00", "created_at": "2025-11-13T18:58:22+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1 Chat", "short_name": "GPT-5.1 Chat", "author": "openai", "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.1 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.\n", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-chat-20251113", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f27c561c-0804-4e51-a96e-18bc1968212d", "name": "OpenAI | openai/gpt-5.1-chat-20251113", "context_length": 128000, "model": { "slug": "openai/gpt-5.1-chat", "hf_slug": "", "updated_at": "2025-11-13T18:58:22.624591+00:00", "created_at": "2025-11-13T18:58:22+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1 Chat", "short_name": "GPT-5.1 Chat", "author": "openai", "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.1 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.\n", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-chat-20251113", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.1-chat", "model_variant_permaslug": "openai/gpt-5.1-chat-20251113", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.1-chat-latest", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "structured_outputs", "response_format", "seed", "max_tokens", "tool_choice", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "2e4eef73-9912-412b-892f-833ea583790a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.1-codex", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-13T18:58:18+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex", "short_name": "GPT-5.1-Codex", "author": "openai", "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-codex-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "58caabab-f2a1-4a27-b098-b46b924efd27", "name": "OpenAI | openai/gpt-5.1-codex-20251113", "context_length": 400000, "model": { "slug": "openai/gpt-5.1-codex", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-11-13T18:58:18+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex", "short_name": "GPT-5.1-Codex", "author": "openai", "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-codex-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.1-codex", "model_variant_permaslug": "openai/gpt-5.1-codex-20251113", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.1-codex", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "700f737d-f192-40f9-8c4a-c74b295e3881", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5.1-codex-mini", "hf_slug": "", "updated_at": "2025-11-13T18:54:22.09584+00:00", "created_at": "2025-11-13T18:17:00.379348+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex-Mini", "short_name": "GPT-5.1-Codex-Mini", "author": "openai", "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-codex-mini-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "27923ab8-2d0e-47ac-b04c-fc79d77ddbd5", "name": "OpenAI | openai/gpt-5.1-codex-mini-20251113", "context_length": 400000, "model": { "slug": "openai/gpt-5.1-codex-mini", "hf_slug": "", "updated_at": "2025-11-13T18:54:22.09584+00:00", "created_at": "2025-11-13T18:17:00.379348+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5.1-Codex-Mini", "short_name": "GPT-5.1-Codex-Mini", "author": "openai", "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5.1-codex-mini-20251113", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5.1-codex-mini", "model_variant_permaslug": "openai/gpt-5.1-codex-mini-20251113", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5.1-codex-mini", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000025", "completion": "0.000002", "input_cache_read": "0.000000025", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 2.5e-7, "openai_responses:completion_tokens": 0.000002, "openai_responses:cached_prompt_tokens": 2.5e-8 }, "pricing_version_id": "b2297b73-9598-4b1a-942f-fdcb3733ddf5", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "amazon/nova-premier-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-31T22:38:52.074161+00:00", "hf_updated_at": null, "name": "Amazon: Nova Premier 1.0", "short_name": "Nova Premier 1.0", "author": "amazon", "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "amazon/nova-premier-v1", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "6e4da481-6c8d-45d0-a3f5-11a9ba527485", "name": "Amazon Bedrock | amazon/nova-premier-v1", "context_length": 1000000, "model": { "slug": "amazon/nova-premier-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-31T22:38:52.074161+00:00", "hf_updated_at": null, "name": "Amazon: Nova Premier 1.0", "short_name": "Nova Premier 1.0", "author": "amazon", "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "amazon/nova-premier-v1", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "amazon/nova-premier-v1", "model_variant_permaslug": "amazon/nova-premier-v1", "adapter_name": "AmazonBedrockConverseAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.amazon.nova-premier-v1:0\t", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.0000025", "completion": "0.0000125", "image": "0", "request": "0", "input_cache_read": "0.000000625", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "perplexity/sonar-pro-search", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-30T19:59:26+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Pro Search", "short_name": "Sonar Pro Search", "author": "perplexity", "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.\n\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "perplexity/sonar-pro-search", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "c78926bd-fa25-4883-8794-22de8c1ce79c", "name": "Perplexity | perplexity/sonar-pro-search", "context_length": 200000, "model": { "slug": "perplexity/sonar-pro-search", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-30T19:59:26+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Pro Search", "short_name": "Sonar Pro Search", "author": "perplexity", "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.\n\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "perplexity/sonar-pro-search", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "perplexity/sonar-pro-search", "model_variant_permaslug": "perplexity/sonar-pro-search", "adapter_name": "PerplexityAdapter", "provider_name": "Perplexity", "provider_info": { "name": "Perplexity", "displayName": "Perplexity", "slug": "perplexity", "baseUrl": "https://api.perplexity.ai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "PerplexityAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.perplexity.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Perplexity.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Perplexity", "provider_slug": "perplexity", "provider_model_id": "sonar-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "frequency_penalty", "presence_penalty", "web_search_options", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "image": "0", "request": "0.018", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.022" }, { "type": "search-threshold", "threshold": "medium", "request": "0.018" }, { "type": "search-threshold", "threshold": "low", "request": "0.014" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "nvidia/nemotron-nano-12b-v2-vl", "hf_slug": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "updated_at": "2025-11-12T02:19:07.557675+00:00", "created_at": "2025-10-28T18:19:25.723503+00:00", "hf_updated_at": null, "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)", "short_name": "Nemotron Nano 12B 2 VL (free)", "author": "nvidia", "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "nvidia/nemotron-nano-12b-v2-vl", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "28304d1d-c2b9-4291-ba4d-dc63e798227e", "name": "Nvidia | nvidia/nemotron-nano-12b-v2-vl:free", "context_length": 128000, "model": { "slug": "nvidia/nemotron-nano-12b-v2-vl", "hf_slug": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "updated_at": "2025-11-12T02:19:07.557675+00:00", "created_at": "2025-10-28T18:19:25.723503+00:00", "hf_updated_at": null, "name": "NVIDIA: Nemotron Nano 12B 2 VL", "short_name": "Nemotron Nano 12B 2 VL", "author": "nvidia", "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "nvidia/nemotron-nano-12b-v2-vl", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "nvidia/nemotron-nano-12b-v2-vl:free", "model_variant_permaslug": "nvidia/nemotron-nano-12b-v2-vl:free", "adapter_name": "OpenAIAdapter", "provider_name": "Nvidia", "provider_info": { "name": "Nvidia", "displayName": "NVIDIA", "slug": "nvidia", "baseUrl": "https://1afcd6e8-59bf-4102-95ed-7ec410f6959f.invocation.api.nvcf.nvidia.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf", "privacyPolicyURL": "https://www.nvidia.com/en-us/about-nvidia/privacy-policy/" }, "headquarters": "US", "datacenters": [ "US" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": true, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NVIDIA", "provider_slug": "nvidia", "provider_model_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "temperature", "max_tokens", "seed", "top_p", "tool_choice", "tools" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": true, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf", "privacyPolicyURL": "https://www.nvidia.com/en-us/about-nvidia/privacy-policy/" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0", "openai:completion_tokens": "0", "openai:cached_prompt_tokens": "0" }, "pricing_version_id": "f11f3cb2-257d-47c5-a74a-4d3c7fb63962", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_base64_video_input": true, "supports_video_urls": true, "disable_free_endpoint_limits": false, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "nvidia/nemotron-nano-12b-v2-vl", "hf_slug": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "updated_at": "2025-11-12T02:19:07.557675+00:00", "created_at": "2025-10-28T18:19:25.723503+00:00", "hf_updated_at": null, "name": "NVIDIA: Nemotron Nano 12B 2 VL", "short_name": "Nemotron Nano 12B 2 VL", "author": "nvidia", "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "nvidia/nemotron-nano-12b-v2-vl", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "da29268d-2dd6-4eb5-bb11-1f5a1f86b91a", "name": "DeepInfra | nvidia/nemotron-nano-12b-v2-vl", "context_length": 131072, "model": { "slug": "nvidia/nemotron-nano-12b-v2-vl", "hf_slug": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "updated_at": "2025-11-12T02:19:07.557675+00:00", "created_at": "2025-10-28T18:19:25.723503+00:00", "hf_updated_at": null, "name": "NVIDIA: Nemotron Nano 12B 2 VL", "short_name": "Nemotron Nano 12B 2 VL", "author": "nvidia", "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "nvidia/nemotron-nano-12b-v2-vl", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "nvidia/nemotron-nano-12b-v2-vl", "model_variant_permaslug": "nvidia/nemotron-nano-12b-v2-vl", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/fp8", "provider_model_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.0000002", "completion": "0.0000006", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000002", "openai:completion_tokens": "0.0000006" }, "pricing_version_id": "43757121-36e7-49de-814c-1f542ffb49ae", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-32b-instruct", "hf_slug": "Qwen/Qwen3-VL-32B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-23T14:55:32.53917+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 32B Instruct", "short_name": "Qwen3 VL 32B Instruct", "author": "qwen", "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen3-vl-32b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "cc9ec262-af0e-4a84-9ce3-218a517f85b3", "name": "Together | qwen/qwen3-vl-32b-instruct", "context_length": 262144, "model": { "slug": "qwen/qwen3-vl-32b-instruct", "hf_slug": "Qwen/Qwen3-VL-32B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-23T14:55:32.53917+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 32B Instruct", "short_name": "Qwen3 VL 32B Instruct", "author": "qwen", "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen3-vl-32b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-32b-instruct", "model_variant_permaslug": "qwen/qwen3-vl-32b-instruct", "adapter_name": "TogetherAdapter", "provider_name": "Together", "provider_info": { "name": "Together", "displayName": "Together", "slug": "together", "baseUrl": "https://api.together.xyz/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "TogetherAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.together.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256" }, "ignoredProviderModels": [ "mixedbread-ai/Mxbai-Rerank-Large-V2", "BAAI/bge-base-en-v1.5-vllm", "scb10x/scb10x-typhoon-2-1-gemma3-12b", "arcee-ai/AFM-4.5B-Preview", "deepseek-ai/DeepSeek-R1-0528-tput", "black-forest-labs/FLUX.1-kontext-dev", "google/gemma-3-27b-it", "Qwen/Qwen3-32B-FP8", "openai/whisper-large-v3", "eddie/Qwen3-32B", "eddiehou/meta-llama/Llama-3.1-405B", "yan/deepseek-ai-deepseek-v3", "moz/Llama-3.3-70B-Instruct-Turbo", "serverless-qwen-qwen3-32b-fp8", "qwen-qwen3-32b-fp8-serverless", "moz-llama-3-3-70b-instruct-turbo", "moonshotai/Kimi-K2-Instruct-tgl-testing", "VirtueAIxTogether/VirtueGuard-Text-Lite", "Virtue-AI/VirtueGuard-Text-Lite", "black-forest-labs/FLUX.1-krea-dev", "prosus/qwen-qwen3-32b-fp8-long-context", "meta-llama/Llama-4-Scout-17B-16E-Instruct-batch", "deepseek-ai/DeepSeek-R1-DE", "arize-ai/qwen-2-1.5b-instruct", "openai/gpt-oss-120b", "meta-llama/Llama-3-70b-hf", "Qwen/Qwen2.5-72B-Instruct", "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference", "meta-llama/Llama-3.2-1B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference", "meta-llama/Meta-Llama-3-8B-Instruct", "meta-llama/Llama-3.1-405B-Instruct", "cartesia/sonic", "cartesia/sonic-2", "togethercomputer/MoA-1", "Salesforce/Llama-Rank-V1", "black-forest-labs/FLUX.1-schnell", "lgai/exaone-3-5-32b-instruct", "lgai/exaone-deep-32b", "black-forest-labs/FLUX.1-dev", "marin-community/marin-8b-instruct", "togethercomputer/Refuel-Llm-V2-Small", "meta-llama/Llama-3-70b-chat-hf", "Alibaba-NLP/gte-modernbert-base", "black-forest-labs/FLUX.1-pro", "black-forest-labs/FLUX.1.1-pro", "togethercomputer/MoA-1-Turbo", "black-forest-labs/FLUX.1-dev-lora", "meta-llama/Llama-2-70b-hf", "togethercomputer/m2-bert-80M-32k-retrieval", "togethercomputer/Refuel-Llm-V2", "intfloat/multilingual-e5-large-instruct", "black-forest-labs/FLUX.1-kontext-max", "black-forest-labs/FLUX.1-schnell-Free", "black-forest-labs/FLUX.1-kontext-pro", "BAAI/bge-large-en-v1.5", "BAAI/bge-base-en-v1.5", "Qwen/Qwen3-Next-80B-A3B-Instruct", "ServiceNow-AI/Apriel-1.5-15b-Thinker", "openai/whisper-large-v3-test", "codellama/CodeLlama-34b-Instruct-hf", "meta-llama/Llama-2-13b-chat-hf", "togethercomputer/m2-bert-80M-8k-retrieval", "WhereIsAI/UAE-Large-V1", "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro", "togethercomputer/m2-bert-80M-2k-retrieval", "meta-llama/Meta-Llama-3-70B-Instruct-Lite", "Meta-Llama/Llama-Guard-7b", "Gryphe/MythoMax-L2-13b-Lite", "upstage/SOLAR-10.7B-Instruct-v1.0", "Qwen/Qwen2.5-14B-Instruct", "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free", "zai-org/GLM-4.5-Air-FP8", "kwaivgI/kling-1.6-standard", "HiDream-ai/HiDream-I1-Full", "ByteDance-Seed/Seedream-3.0", "ByteDance-Seed/Seedream-4.0", "Lykon/DreamShaper", "HiDream-ai/HiDream-I1-Dev", "Qwen/Qwen-Image", "RunDiffusion/Juggernaut-pro-flux", "google/imagen-4.0-preview", "google/imagen-4.0-ultra", "google/veo-3.0", "minimax/hailuo-02", "stabilityai/stable-diffusion-3-medium", "black-forest-labs/FLUX.1-Canny-pro", "google/imagen-4.0-fast", "minimax/video-01-director", "HiDream-ai/HiDream-I1-Fast", "Wan-AI/Wan2.2-T2V-A14B", "ByteDance/Seedance-1.0-pro", "google/veo-3.0-fast-audio", "vidu/vidu-q1", "kwaivgI/kling-2.1-master", "google/veo-3.0-audio", "Rundiffusion/Juggernaut-Lightning-Flux", "Wan-AI/Wan2.2-I2V-A14B", "google/flash-image-2.5", "google/veo-2.0", "openai/sora-2", "google/veo-3.0-fast", "ideogram/ideogram-3.0", "kwaivgI/kling-2.0-master", "kwaivgI/kling-2.1-standard", "pixverse/pixverse-v5", "stabilityai/stable-diffusion-xl-base-1.0", "openai/sora-2-pro", "ByteDance/Seedance-1.0-lite", "kwaivgI/kling-1.6-pro", "vidu/vidu-2.0", "kwaivgI/kling-2.1-pro", "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "canopylabs/orpheus-3b-0.1-ft", "hexgrad/Kokoro-82M", "eddie/gemma-2b-it", "mistralai/Voxtral-Mini-3B-2507", "arcee-ai/coder-large", "arcee-ai/virtuoso-large", "arcee-ai/maestro-reasoning", "deepcogito/cogito-v2-1-671b", "arcee_ai/arcee-spotlight", "google/gemini-3-pro-image", "mercor/cwm", "black-forest-labs/FLUX.2-flex", "keith-aditya/kimi-k2-instruct", "pangram/mistral-small-2501", "black-forest-labs/FLUX.2-pro", "black-forest-labs/FLUX.2-dev", "ServiceNow-AI/Apriel-1.6-15b-Thinker" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Together", "provider_slug": "together", "provider_model_id": "Qwen/Qwen3-VL-32B-Instruct", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "top_k", "repetition_penalty", "logit_bias", "min_p", "structured_outputs", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "pricing": { "prompt": "0.0000005", "completion": "0.0000015", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000005", "openai:completion_tokens": "0.0000015" }, "pricing_version_id": "65677213-46f1-457c-abb0-4cfeaec61a6f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-image-mini", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-16T14:23:03.143259+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Image Mini", "short_name": "GPT-5 Image Mini", "author": "openai", "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-image-mini", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "7c09094a-64ec-4d53-bd69-c165ac31c465", "name": "OpenAI | openai/gpt-5-image-mini", "context_length": 400000, "model": { "slug": "openai/gpt-5-image-mini", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-16T14:23:03.143259+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Image Mini", "short_name": "GPT-5 Image Mini", "author": "openai", "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-image-mini", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-image-mini", "model_variant_permaslug": "openai/gpt-5-image-mini", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-mini-2025-08-07", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000025", "completion": "0.000002", "input_cache_read": "0.00000025", "web_search": "0.01", "image_output": "0.000008", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.0000025, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000002, "openai_responses:image_output_tokens": 0.000008, "openai_responses:cached_prompt_tokens": 2.5e-7 }, "pricing_version_id": "f2440c26-2f98-41c2-8d81-fcbca956e29a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-haiku-4.5", "hf_slug": "", "updated_at": "2025-12-05T21:53:18.541396+00:00", "created_at": "2025-10-15T17:00:38+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Haiku 4.5", "short_name": "Claude Haiku 4.5", "author": "anthropic", "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-haiku-20251001", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "8a5e69a1-ea0d-4af6-899e-8b7e1c93a7a9", "name": "Google | anthropic/claude-4.5-haiku-20251001", "context_length": 200000, "model": { "slug": "anthropic/claude-haiku-4.5", "hf_slug": "", "updated_at": "2025-12-05T21:53:18.541396+00:00", "created_at": "2025-10-15T17:00:38+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Haiku 4.5", "short_name": "Claude Haiku 4.5", "author": "anthropic", "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-haiku-20251001", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-haiku-4.5", "model_variant_permaslug": "anthropic/claude-4.5-haiku-20251001", "adapter_name": "GoogleVertexAnthropicAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "claude-haiku-4-5@20251001", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "top_p", "temperature", "stop", "reasoning", "include_reasoning", "tools", "tool_choice", "top_k" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000001", "completion": "0.000005", "input_cache_read": "0.0000001", "input_cache_write": "0.00000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000001, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 1e-7, "anthropic:completion_tokens": 0.000005, "anthropic:cache_write_1h_tokens": 0.000002, "anthropic:cache_write_5m_tokens": 0.00000125 }, "pricing_version_id": "2f1bce8a-465d-4d77-9efa-5f1c83f908dc", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_native_web_search": false, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": "global", "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-8b-thinking", "hf_slug": "Qwen/Qwen3-VL-8B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-14T17:42:26.552544+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 8B Thinking", "short_name": "Qwen3 VL 8B Thinking", "author": "qwen", "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\n\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-8b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 1, "top_p": 0.95 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "6cb46014-347b-4d67-aefa-7b83e065b8c3", "name": "Alibaba | qwen/qwen3-vl-8b-thinking", "context_length": 256000, "model": { "slug": "qwen/qwen3-vl-8b-thinking", "hf_slug": "Qwen/Qwen3-VL-8B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-14T17:42:26.552544+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 8B Thinking", "short_name": "Qwen3 VL 8B Thinking", "author": "qwen", "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\n\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-8b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 1, "top_p": 0.95 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-8b-thinking", "model_variant_permaslug": "qwen/qwen3-vl-8b-thinking", "adapter_name": "AlibabaAdapter", "provider_name": "Alibaba", "provider_info": { "name": "Alibaba", "displayName": "Alibaba Cloud Int.", "slug": "alibaba", "baseUrl": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "headquarters": "SG", "datacenters": [ "SG", "CN" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AlibabaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.alibabacloud.com/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Alibaba Cloud Int.", "provider_slug": "alibaba", "provider_model_id": "qwen3-vl-8b-thinking", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "presence_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "pricing": { "prompt": "0.00000018", "completion": "0.0000021", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-8b-instruct", "hf_slug": "Qwen/Qwen3-VL-8B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-14T17:35:08.402158+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 8B Instruct", "short_name": "Qwen3 VL 8B Instruct", "author": "qwen", "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\n\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-8b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "6bfd6b5b-ff8c-436f-ae3f-d28c02bcfce3", "name": "Novita | qwen/qwen3-vl-8b-instruct", "context_length": 131072, "model": { "slug": "qwen/qwen3-vl-8b-instruct", "hf_slug": "Qwen/Qwen3-VL-8B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-14T17:35:08.402158+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 8B Instruct", "short_name": "Qwen3 VL 8B Instruct", "author": "qwen", "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\n\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-8b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-8b-instruct", "model_variant_permaslug": "qwen/qwen3-vl-8b-instruct", "adapter_name": "NovitaAdapter", "provider_name": "Novita", "provider_info": { "name": "Novita", "displayName": "NovitaAI", "slug": "novita", "baseUrl": "https://api.novita.ai/v3/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P2zP0TCZwbzCC8QkH8m8o1i8M" ], "adapterName": "NovitaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.novita.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256" }, "ignoredProviderModels": [ "google/gemma-3-1b-it", "baichuan/baichuan-m2-32b", "baidu/ernie-4.5-0.3b", "qwen/qwen-mt-plus", "qwen/qwen3-4b-fp8", "meta-llama/llama-3.2-1b-instruct", "sophosympatheia/midnight-rose-70b", "deepseek/deepseek-prover-v2-671b", "Sao10K/L3-8B-Stheno-v3.2", "thudm/glm-4-32b-0414", "qwen/qwen3-omni-30b-a3b-thinking", "qwen/qwen3-omni-30b-a3b-instruct", "paddlepaddle/paddleocr-vl", "deepseek/deepseek-ocr", "skywork/r1v4-lite", "baidu/ernie-4.5-vl-28b-a3b-thinking", "zai-org/autoglm-phone-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NovitaAI", "provider_slug": "novita/fp8", "provider_model_id": "qwen/qwen3-vl-8b-instruct", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "pricing": { "prompt": "0.00000008", "completion": "0.0000005", "image": "0", "request": "0", "input_cache_read": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000008", "openai:completion_tokens": "0.0000005" }, "pricing_version_id": "9e2dd497-044e-4748-b403-b4743fad861d", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-image", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-14T13:19:46.029021+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Image", "short_name": "GPT-5 Image", "author": "openai", "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-image", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "be0ed145-8bfc-4aec-a62d-685ed334fe17", "name": "OpenAI | openai/gpt-5-image", "context_length": 400000, "model": { "slug": "openai/gpt-5-image", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-14T13:19:46.029021+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Image", "short_name": "GPT-5 Image", "author": "openai", "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-image", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "image_generation", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-image", "model_variant_permaslug": "openai/gpt-5-image", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-2025-08-07", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00001", "completion": "0.00001", "input_cache_read": "0.00000125", "web_search": "0.01", "image_output": "0.00004", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00001, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:image_output_tokens": 0.00004, "openai_responses:cached_prompt_tokens": 0.00000125 }, "pricing_version_id": "b9d2cf4c-5f0e-41c0-b7ba-082300d4a127", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o3-deep-research", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-10T20:54:21.971349+00:00", "hf_updated_at": null, "name": "OpenAI: o3 Deep Research", "short_name": "o3 Deep Research", "author": "openai", "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/o3-deep-research-2025-06-26", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "a697c6df-cbb4-4a6b-8b1e-04e92f00146a", "name": "OpenAI | openai/o3-deep-research-2025-06-26", "context_length": 200000, "model": { "slug": "openai/o3-deep-research", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-10T20:54:21.971349+00:00", "hf_updated_at": null, "name": "OpenAI: o3 Deep Research", "short_name": "o3 Deep Research", "author": "openai", "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/o3-deep-research-2025-06-26", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o3-deep-research", "model_variant_permaslug": "openai/o3-deep-research-2025-06-26", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o3-deep-research-2025-06-26", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00001", "completion": "0.00004", "input_cache_read": "0.0000025", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00001, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00004, "openai_responses:cached_prompt_tokens": 0.0000025 }, "pricing_version_id": "46ca33ba-23c1-4a17-a248-30cb67033660", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o4-mini-deep-research", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-10T20:54:02.725273+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini Deep Research", "short_name": "o4 Mini Deep Research", "author": "openai", "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/o4-mini-deep-research-2025-06-26", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "97f9f7c3-9e55-4f6d-8de4-459d4f23e2a9", "name": "OpenAI | openai/o4-mini-deep-research-2025-06-26", "context_length": 200000, "model": { "slug": "openai/o4-mini-deep-research", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-10T20:54:02.725273+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini Deep Research", "short_name": "o4 Mini Deep Research", "author": "openai", "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/o4-mini-deep-research-2025-06-26", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o4-mini-deep-research", "model_variant_permaslug": "openai/o4-mini-deep-research-2025-06-26", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o4-mini-deep-research-2025-06-26", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000002", "completion": "0.000008", "input_cache_read": "0.0000005", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.000002, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000008, "openai_responses:cached_prompt_tokens": 5e-7 }, "pricing_version_id": "aecfa236-8c7d-479b-b3fe-7450fb7d299f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-flash-image", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-07T20:53:51+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Image (Nano Banana)", "short_name": "Gemini 2.5 Flash Image (Nano Banana)", "author": "google", "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-image", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "2341e1bc-99ea-46ab-ae2d-9a83846afb43", "name": "Google AI Studio | google/gemini-2.5-flash-image", "context_length": 32768, "model": { "slug": "google/gemini-2.5-flash-image", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-07T20:53:51+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Image (Nano Banana)", "short_name": "Gemini 2.5 Flash Image (Nano Banana)", "author": "google", "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-image", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-flash-image", "model_variant_permaslug": "google/gemini-2.5-flash-image", "adapter_name": "GoogleAIStudioGeminiAdapter", "provider_name": "Google AI Studio", "provider_info": { "name": "Google AI Studio", "displayName": "Google AI Studio", "slug": "google-ai-studio", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleAIStudioGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "/images/icons/GoogleAIStudio.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-1p", "gemini-2.5-pro-1p-recitation-off", "gemini-2.5-flash-1p", "gemini-2.5-flash-1p-recitation-off", "gemini-2.5-flash-lite-preview-06-11-summarized", "gemini-2.5-flash", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-1.5-pro-latest", "gemini-1.5-pro", "gemini-1.5-flash-latest", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-1.5-flash-8b-latest", "gemini-2.5-pro-preview-03-25", "gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-preview", "gemini-2.0-pro-exp", "gemini-2.0-flash-thinking-exp", "gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts", "learnlm-2.0-flash-experimental", "gracefulgolem", "gemini-2.5-flash-preview-05-20", "gemini-2.5-pro-preview-06-05", "gemini-2.0-flash-exp-image-generation", "gemini-2.0-flash-preview-image-generation", "gemini-2.0-flash-lite-preview-02-05", "gemini-2.0-pro-exp-02-05", "gemini-exp-1206", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-flash-thinking-exp-1219", "gemma-3-1b-it", "gemini-flash-latest", "gemini-flash-lite-latest", "gemini-pro-latest", "gemini-robotics-er-1.5-preview", "gemini-embedding-001", "riftrunner-fst-rewind", "gemini-3-pro-image-preview", "nano-banana-pro-preview", "fiercefalcon", "fiercefalcon-inline-citation", "fiercefalcon-blocked-sites" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google AI Studio", "provider_slug": "google-ai-studio", "provider_model_id": "gemini-2.5-flash-image", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "pricing": { "prompt": "0.0000003", "completion": "0.0000025", "image": "0.0000003", "audio": "0.000001", "input_audio_cache": "0.0000001", "input_cache_read": "0.00000003", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000025", "image_output": "0.00003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 3e-7, "gemini:reasoning_tokens": 0.0000025, "gemini:cache_read_tokens": 3e-8, "gemini:completion_tokens": 0.0000025, "gemini:text_input_tokens": 3e-7, "gemini:audio_input_tokens": 0.000001, "gemini:image_input_tokens": 3e-7, "gemini:video_input_tokens": 3e-7, "gemini:image_output_tokens": 0.00003, "gemini:cache_read_text_tokens": 3e-8, "gemini:cache_read_audio_tokens": 1e-7, "gemini:cache_read_image_tokens": 3e-8, "gemini:cache_read_video_tokens": 3e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 1e-7, "gemini:cache_read_text_tokens_high_context": 1e-7, "gemini:cache_read_audio_tokens_high_context": 2e-7, "gemini:cache_read_image_tokens_high_context": 1e-7, "gemini:cache_read_video_tokens_high_context": 1e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "549376c3-3914-47e7-9801-c410ca4dc4dd", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": 1000, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-30b-a3b-thinking", "hf_slug": "Qwen/Qwen3-VL-30B-A3B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-06T23:47:59.575824+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 30B A3B Thinking", "short_name": "Qwen3 VL 30B A3B Thinking", "author": "qwen", "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-30b-a3b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 0.8, "top_p": 0.95 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "38ee90ad-31ec-4a90-925c-a95d9829636a", "name": "Novita | qwen/qwen3-vl-30b-a3b-thinking", "context_length": 131072, "model": { "slug": "qwen/qwen3-vl-30b-a3b-thinking", "hf_slug": "Qwen/Qwen3-VL-30B-A3B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-06T23:47:59.575824+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 30B A3B Thinking", "short_name": "Qwen3 VL 30B A3B Thinking", "author": "qwen", "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.", "model_version_group_id": null, "context_length": 0, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-30b-a3b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 0.8, "top_p": 0.95 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-30b-a3b-thinking", "model_variant_permaslug": "qwen/qwen3-vl-30b-a3b-thinking", "adapter_name": "NovitaAdapter", "provider_name": "Novita", "provider_info": { "name": "Novita", "displayName": "NovitaAI", "slug": "novita", "baseUrl": "https://api.novita.ai/v3/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P2zP0TCZwbzCC8QkH8m8o1i8M" ], "adapterName": "NovitaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.novita.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256" }, "ignoredProviderModels": [ "google/gemma-3-1b-it", "baichuan/baichuan-m2-32b", "baidu/ernie-4.5-0.3b", "qwen/qwen-mt-plus", "qwen/qwen3-4b-fp8", "meta-llama/llama-3.2-1b-instruct", "sophosympatheia/midnight-rose-70b", "deepseek/deepseek-prover-v2-671b", "Sao10K/L3-8B-Stheno-v3.2", "thudm/glm-4-32b-0414", "qwen/qwen3-omni-30b-a3b-thinking", "qwen/qwen3-omni-30b-a3b-instruct", "paddlepaddle/paddleocr-vl", "deepseek/deepseek-ocr", "skywork/r1v4-lite", "baidu/ernie-4.5-vl-28b-a3b-thinking", "zai-org/autoglm-phone-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NovitaAI", "provider_slug": "novita/fp16", "provider_model_id": "qwen/qwen3-vl-30b-a3b-thinking", "quantization": "fp16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "pricing": { "prompt": "0.0000002", "completion": "0.000001", "image": "0", "request": "0", "input_cache_read": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000002", "openai:completion_tokens": "0.000001" }, "pricing_version_id": "5224499e-cd5b-4c1e-a1ff-a79b4af53aa1", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-30b-a3b-instruct", "hf_slug": "Qwen/Qwen3-VL-30B-A3B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-06T23:47:56.430294+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 30B A3B Instruct", "short_name": "Qwen3 VL 30B A3B Instruct", "author": "qwen", "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-30b-a3b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "dbb294c1-20cd-4d67-b225-2ff03a050cc8", "name": "Fireworks | qwen/qwen3-vl-30b-a3b-instruct", "context_length": 262144, "model": { "slug": "qwen/qwen3-vl-30b-a3b-instruct", "hf_slug": "Qwen/Qwen3-VL-30B-A3B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-06T23:47:56.430294+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 30B A3B Instruct", "short_name": "Qwen3 VL 30B A3B Instruct", "author": "qwen", "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-30b-a3b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-30b-a3b-instruct", "model_variant_permaslug": "qwen/qwen3-vl-30b-a3b-instruct", "adapter_name": "FireworksAdapter", "provider_name": "Fireworks", "provider_info": { "name": "Fireworks", "displayName": "Fireworks", "slug": "fireworks", "baseUrl": "https://api.fireworks.ai/inference/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://fireworks.ai/terms-of-service", "privacyPolicyURL": "https://fireworks.ai/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34k70EDz4tN23XFsU2l3tSqm4wF" ], "adapterName": "FireworksAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.fireworks.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Fireworks.png" }, "ignoredProviderModels": [ "accounts/fireworks/models/qwen2-vl-72b-instruct", "accounts/fireworks/models/llama4-scout-instruct-basic", "accounts/scale-ai/models/arctic-text2sql-r1-7b-public", "accounts/fireworks/models/qwen3-embedding-8b", "accounts/fireworks/models/glm-4p5-air", "accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "accounts/lukablaskovic2000-738cce/models/bio-mistral-7b", "accounts/perplexity/models/r1-1776", "accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new", "accounts/fireworks/models/qwen3-reranker-8b", "accounts/fireworks/models/deepseek-v3p1-terminus", "accounts/sentientfoundation-serverless/models/dobby-mini-unhinged-plus-llama-3-1-8b", "accounts/fireworks/models/deepseek-r1-basic" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Fireworks", "provider_slug": "fireworks", "provider_model_id": "accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "top_k", "repetition_penalty", "logit_bias", "logprobs", "top_logprobs", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://fireworks.ai/terms-of-service", "privacyPolicyURL": "https://fireworks.ai/privacy-policy" }, "pricing": { "prompt": "0.00000015", "completion": "0.0000006", "input_cache_read": "0.000000075", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000015", "openai:completion_tokens": "0.0000006", "openai:cached_prompt_tokens": "0.000000075" }, "pricing_version_id": "589bf4b0-9c5c-4004-a748-58881360475c", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-pro", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-06T18:51:03.215373+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Pro", "short_name": "GPT-5 Pro", "author": "openai", "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-pro-2025-10-06", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "86e3e664-d291-415d-a769-8e08b96a79e9", "name": "OpenAI | openai/gpt-5-pro-2025-10-06", "context_length": 400000, "model": { "slug": "openai/gpt-5-pro", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-10-06T18:51:03.215373+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Pro", "short_name": "GPT-5 Pro", "author": "openai", "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-pro-2025-10-06", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": [ "high" ], "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-pro", "model_variant_permaslug": "openai/gpt-5-pro-2025-10-06", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-pro-2025-10-06", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000015", "completion": "0.00012", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.000015, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00012 }, "pricing_version_id": "f10148f9-4c52-440d-8ba0-7b474ed90068", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-sonnet-4.5", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-29T16:01:16.552976+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Sonnet 4.5", "short_name": "Claude Sonnet 4.5", "author": "anthropic", "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-sonnet-20250929", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 1, "top_p": 1, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d8bee848-f020-454a-b2be-4a7ce868f99f", "name": "Amazon Bedrock | anthropic/claude-4.5-sonnet-20250929", "context_length": 1000000, "model": { "slug": "anthropic/claude-sonnet-4.5", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-29T16:01:16.552976+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Sonnet 4.5", "short_name": "Claude Sonnet 4.5", "author": "anthropic", "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "anthropic/claude-4.5-sonnet-20250929", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 1, "top_p": 1, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-sonnet-4.5", "model_variant_permaslug": "anthropic/claude-4.5-sonnet-20250929", "adapter_name": "AmazonBedrockInvokeAnthropicAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "input_cache_read": "0.0000003", "input_cache_write": "0.00000375", "web_search": "0.01", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.000006", "completions": "0.0000225", "input_cache_read": "0.0000006", "input_cache_write": "0.0000075" } ], "pricing_json": { "anthropic:prompt_tokens": 0.000003, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 3e-7, "anthropic:completion_tokens": 0.000015, "anthropic:cache_write_1h_tokens": 0.000006, "anthropic:cache_write_5m_tokens": 0.00000375, "anthropic:long_context_threshold": 200000, "anthropic:prompt_tokens_long_context": 0.000006, "anthropic:cache_read_tokens_long_context": 6e-7, "anthropic:completion_tokens_long_context": 0.0000225, "anthropic:cache_write_1h_tokens_long_context": 0.000012, "anthropic:cache_write_5m_tokens_long_context": 0.0000075 }, "pricing_version_id": "f1afe5e8-55e9-4d00-bc49-33b73ac3d69e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-flash-preview-09-2025", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-25T17:09:38.646963+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Preview 09-2025", "short_name": "Gemini 2.5 Flash Preview 09-2025", "author": "google", "description": "Gemini 2.5 Flash Preview September 2025 Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "image", "file", "text", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-preview-09-2025", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "3135cae6-b7a4-49be-9994-12aebe3caf27", "name": "Google | google/gemini-2.5-flash-preview-09-2025", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-flash-preview-09-2025", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-25T17:09:38.646963+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Preview 09-2025", "short_name": "Gemini 2.5 Flash Preview 09-2025", "author": "google", "description": "Gemini 2.5 Flash Preview September 2025 Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "image", "file", "text", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-preview-09-2025", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-flash-preview-09-2025", "model_variant_permaslug": "google/gemini-2.5-flash-preview-09-2025", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex (Global)", "slug": "google-vertex/global", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex (Global)", "provider_slug": "google-vertex/global", "provider_model_id": "gemini-2.5-flash-preview-09-2025", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000003", "completion": "0.0000025", "image": "0.0000003", "audio": "0.000001", "input_audio_cache": "0.0000001", "input_cache_read": "0.00000003", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000025", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 3e-7, "gemini:reasoning_tokens": 0.0000025, "gemini:cache_read_tokens": 3e-8, "gemini:completion_tokens": 0.0000025, "gemini:text_input_tokens": 3e-7, "gemini:audio_input_tokens": 0.000001, "gemini:image_input_tokens": 3e-7, "gemini:video_input_tokens": 3e-7, "gemini:cache_read_text_tokens": 3e-8, "gemini:cache_read_audio_tokens": 1e-7, "gemini:cache_read_image_tokens": 3e-8, "gemini:cache_read_video_tokens": 3e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 1e-7, "gemini:cache_read_text_tokens_high_context": 1e-7, "gemini:cache_read_audio_tokens_high_context": 2e-7, "gemini:cache_read_image_tokens_high_context": 1e-7, "gemini:cache_read_video_tokens_high_context": 1e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "2fe6cb2f-c190-4a31-bd69-15f6c4b81c84", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_video_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": true }, "provider_region": "global", "deprecation_date": "2026-02-17" } }, { "slug": "google/gemini-2.5-flash-lite-preview-09-2025", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-25T17:01:26.198818+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", "short_name": "Gemini 2.5 Flash Lite Preview 09-2025", "author": "google", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-lite-preview-09-2025", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "6e63b201-b2cc-45d9-b0c0-da687a96efa0", "name": "Google | google/gemini-2.5-flash-lite-preview-09-2025", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-flash-lite-preview-09-2025", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-25T17:01:26.198818+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", "short_name": "Gemini 2.5 Flash Lite Preview 09-2025", "author": "google", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-lite-preview-09-2025", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-flash-lite-preview-09-2025", "model_variant_permaslug": "google/gemini-2.5-flash-lite-preview-09-2025", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.5-flash-lite-preview-09-2025", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000001", "completion": "0.0000004", "image": "0.0000001", "audio": "0.0000003", "input_audio_cache": "0.00000003", "input_cache_read": "0.00000001", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000004", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 1e-7, "gemini:reasoning_tokens": 4e-7, "gemini:cache_read_tokens": 1e-8, "gemini:completion_tokens": 4e-7, "gemini:text_input_tokens": 1e-7, "gemini:audio_input_tokens": 3e-7, "gemini:image_input_tokens": 1e-7, "gemini:video_input_tokens": 1e-7, "gemini:cache_read_text_tokens": 1e-8, "gemini:cache_read_audio_tokens": 3e-8, "gemini:cache_read_image_tokens": 1e-8, "gemini:cache_read_video_tokens": 1e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 3e-8, "gemini:cache_read_text_tokens_high_context": 3e-8, "gemini:cache_read_audio_tokens_high_context": 6e-8, "gemini:cache_read_image_tokens_high_context": 3e-8, "gemini:cache_read_video_tokens_high_context": 3e-8, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "b52b655f-9872-4089-9ec1-fabaaa9f6a5f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-235b-a22b-thinking", "hf_slug": "Qwen/Qwen3-VL-235B-A22B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-09-23T23:04:50+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 235B A22B Thinking", "short_name": "Qwen3 VL 235B A22B Thinking", "author": "qwen", "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-235b-a22b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 0.8, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "37f02013-5c66-4800-bf34-dac4804abd14", "name": "SiliconFlow | qwen/qwen3-vl-235b-a22b-thinking", "context_length": 262144, "model": { "slug": "qwen/qwen3-vl-235b-a22b-thinking", "hf_slug": "Qwen/Qwen3-VL-235B-A22B-Thinking", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-09-23T23:04:50+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 235B A22B Thinking", "short_name": "Qwen3 VL 235B A22B Thinking", "author": "qwen", "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-235b-a22b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": 0.8, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-235b-a22b-thinking", "model_variant_permaslug": "qwen/qwen3-vl-235b-a22b-thinking", "adapter_name": "SiliconFlowAdapter", "provider_name": "SiliconFlow", "provider_info": { "name": "SiliconFlow", "displayName": "SiliconFlow", "slug": "siliconflow", "baseUrl": "https://api.siliconflow.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "SiliconFlowAdapter", "isMultipartSupported": false, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "/images/icons/SiliconFlow.svg" }, "ignoredProviderModels": [ "inclusionAI/Ling-mini-2.0", "inclusionAI/Ring-flash-2.0", "inclusionAI/Ling-flash-2.0" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "SiliconFlow", "provider_slug": "siliconflow/fp8", "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Thinking", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 262144, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "temperature", "top_p", "top_k", "frequency_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "pricing": { "prompt": "0.00000045", "completion": "0.0000035", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000045", "openai:completion_tokens": "0.0000035" }, "pricing_version_id": "75357189-5294-4f42-8678-e406f1c9fbcd", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen3-vl-235b-a22b-instruct", "hf_slug": "Qwen/Qwen3-VL-235B-A22B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-23T23:04:47+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 235B A22B Instruct", "short_name": "Qwen3 VL 235B A22B Instruct", "author": "qwen", "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.", "model_version_group_id": null, "context_length": 262144, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-235b-a22b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "a352cc82-2bdb-411b-9f99-bd7829655412", "name": "DeepInfra | qwen/qwen3-vl-235b-a22b-instruct", "context_length": 262144, "model": { "slug": "qwen/qwen3-vl-235b-a22b-instruct", "hf_slug": "Qwen/Qwen3-VL-235B-A22B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-23T23:04:47+00:00", "hf_updated_at": null, "name": "Qwen: Qwen3 VL 235B A22B Instruct", "short_name": "Qwen3 VL 235B A22B Instruct", "author": "qwen", "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen3", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "qwen/qwen3-vl-235b-a22b-instruct", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.7, "top_p": 0.8, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen3-vl-235b-a22b-instruct", "model_variant_permaslug": "qwen/qwen3-vl-235b-a22b-instruct", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/fp8", "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.0000002", "completion": "0.0000012", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000002", "openai:completion_tokens": "0.0000012" }, "pricing_version_id": "e564dec6-f9d2-4049-bd90-bc07dbd96bd3", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": false, "structured_outputs": false } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-codex", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-09-23T16:03:23.098042+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Codex", "short_name": "GPT-5 Codex", "author": "openai", "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-codex", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f10a63bc-2bcd-4726-9e75-1e482efd080c", "name": "OpenAI | openai/gpt-5-codex", "context_length": 400000, "model": { "slug": "openai/gpt-5-codex", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-09-23T16:03:23.098042+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Codex", "short_name": "GPT-5 Codex", "author": "openai", "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-codex", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-codex", "model_variant_permaslug": "openai/gpt-5-codex", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-codex", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "a7ad56ea-d51d-4add-b41a-b2c02e411b01", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "x-ai/grok-4-fast", "hf_slug": "", "updated_at": "2025-11-19T22:48:00.44912+00:00", "created_at": "2025-09-19T00:01:30.267569+00:00", "hf_updated_at": null, "name": "xAI: Grok 4 Fast", "short_name": "Grok 4 Fast", "author": "x-ai", "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "x-ai/grok-4-fast", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "c9586d9d-97ff-40ca-ae94-22504d6f9b7e", "name": "xAI | x-ai/grok-4-fast", "context_length": 2000000, "model": { "slug": "x-ai/grok-4-fast", "hf_slug": "", "updated_at": "2025-11-19T22:48:00.44912+00:00", "created_at": "2025-09-19T00:01:30.267569+00:00", "hf_updated_at": null, "name": "xAI: Grok 4 Fast", "short_name": "Grok 4 Fast", "author": "x-ai", "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "x-ai/grok-4-fast", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "x-ai/grok-4-fast", "model_variant_permaslug": "x-ai/grok-4-fast", "adapter_name": "XAIResponsesAdapter", "provider_name": "xAI", "provider_info": { "name": "xAI", "displayName": "xAI", "slug": "xai", "baseUrl": "https://api.x.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "XAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.x.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "xAI", "provider_slug": "xai", "provider_model_id": "grok-4-fast-non-reasoning", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 30000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000002", "completion": "0.0000005", "image": "0", "request": "0", "input_cache_read": "0.00000005", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 128000, "prompt": "0.0000004", "completions": "0.000001", "input_cache_read": "0.00000005" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_native_web_search": true, "disable_free_endpoint_limits": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "opengvlab/internvl3-78b", "hf_slug": "OpenGVLab/InternVL3-78B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-15T18:55:55.952936+00:00", "hf_updated_at": null, "name": "OpenGVLab: InternVL3 78B", "short_name": "InternVL3 78B", "author": "opengvlab", "description": "The InternVL3 series is an advanced multimodal large language model (MLLM). Compared to InternVL 2.5, InternVL3 demonstrates stronger multimodal perception and reasoning capabilities. \n\nIn addition, InternVL3 is benchmarked against the Qwen2.5 Chat models, whose pre-trained base models serve as the initialization for its language component. Benefiting from Native Multimodal Pre-Training, the InternVL3 series surpasses the Qwen2.5 series in overall text performance.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "opengvlab/internvl3-78b", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "832d7038-1b47-4530-ba1e-ce6668e1fdfa", "name": "Chutes | opengvlab/internvl3-78b", "context_length": 32768, "model": { "slug": "opengvlab/internvl3-78b", "hf_slug": "OpenGVLab/InternVL3-78B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-15T18:55:55.952936+00:00", "hf_updated_at": null, "name": "OpenGVLab: InternVL3 78B", "short_name": "InternVL3 78B", "author": "opengvlab", "description": "The InternVL3 series is an advanced multimodal large language model (MLLM). Compared to InternVL 2.5, InternVL3 demonstrates stronger multimodal perception and reasoning capabilities. \n\nIn addition, InternVL3 is benchmarked against the Qwen2.5 Chat models, whose pre-trained base models serve as the initialization for its language component. Benefiting from Native Multimodal Pre-Training, the InternVL3 series surpasses the Qwen2.5 series in overall text performance.", "model_version_group_id": null, "context_length": 0, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "opengvlab/internvl3-78b", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "opengvlab/internvl3-78b", "model_variant_permaslug": "opengvlab/internvl3-78b", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "OpenGVLab/InternVL3-78B-TEE", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.0000001", "completion": "0.00000039", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000001", "openai:completion_tokens": "0.00000039" }, "pricing_version_id": "c6552ee8-61f8-4cce-8350-41844cfd6986", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "deepcogito/cogito-v2-preview-llama-109b-moe", "hf_slug": "deepcogito/cogito-v2-preview-llama-109B-MoE", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-02T16:46:08.407814+00:00", "hf_updated_at": null, "name": "Cogito V2 Preview Llama 109B", "short_name": "Cogito V2 Preview Llama 109B", "author": "deepcogito", "description": "An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated Distillation & Amplification (IDA). It targets coding, STEM, instruction following, and general helpfulness, with stronger multilingual, tool-calling, and reasoning performance than size-equivalent baselines. The model supports long-context use (up to 10M tokens) and standard Transformers workflows. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)", "model_version_group_id": null, "context_length": 32767, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "deepcogito/cogito-v2-preview-llama-109b-moe", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": "Enable deep thinking subroutine." }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": "Enable deep thinking subroutine." } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "349f6bd6-3722-4ffd-a1af-cee16a5d6784", "name": "Together | deepcogito/cogito-v2-preview-llama-109b-moe", "context_length": 32767, "model": { "slug": "deepcogito/cogito-v2-preview-llama-109b-moe", "hf_slug": "deepcogito/cogito-v2-preview-llama-109B-MoE", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-02T16:46:08.407814+00:00", "hf_updated_at": null, "name": "Cogito V2 Preview Llama 109B", "short_name": "Cogito V2 Preview Llama 109B", "author": "deepcogito", "description": "An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated Distillation & Amplification (IDA). It targets coding, STEM, instruction following, and general helpfulness, with stronger multilingual, tool-calling, and reasoning performance than size-equivalent baselines. The model supports long-context use (up to 10M tokens) and standard Transformers workflows. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "deepcogito/cogito-v2-preview-llama-109b-moe", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": "Enable deep thinking subroutine." }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": "Enable deep thinking subroutine." } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "deepcogito/cogito-v2-preview-llama-109b-moe", "model_variant_permaslug": "deepcogito/cogito-v2-preview-llama-109b-moe", "adapter_name": "TogetherAdapter", "provider_name": "Together", "provider_info": { "name": "Together", "displayName": "Together", "slug": "together", "baseUrl": "https://api.together.xyz/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "TogetherAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.together.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256" }, "ignoredProviderModels": [ "mixedbread-ai/Mxbai-Rerank-Large-V2", "BAAI/bge-base-en-v1.5-vllm", "scb10x/scb10x-typhoon-2-1-gemma3-12b", "arcee-ai/AFM-4.5B-Preview", "deepseek-ai/DeepSeek-R1-0528-tput", "black-forest-labs/FLUX.1-kontext-dev", "google/gemma-3-27b-it", "Qwen/Qwen3-32B-FP8", "openai/whisper-large-v3", "eddie/Qwen3-32B", "eddiehou/meta-llama/Llama-3.1-405B", "yan/deepseek-ai-deepseek-v3", "moz/Llama-3.3-70B-Instruct-Turbo", "serverless-qwen-qwen3-32b-fp8", "qwen-qwen3-32b-fp8-serverless", "moz-llama-3-3-70b-instruct-turbo", "moonshotai/Kimi-K2-Instruct-tgl-testing", "VirtueAIxTogether/VirtueGuard-Text-Lite", "Virtue-AI/VirtueGuard-Text-Lite", "black-forest-labs/FLUX.1-krea-dev", "prosus/qwen-qwen3-32b-fp8-long-context", "meta-llama/Llama-4-Scout-17B-16E-Instruct-batch", "deepseek-ai/DeepSeek-R1-DE", "arize-ai/qwen-2-1.5b-instruct", "openai/gpt-oss-120b", "meta-llama/Llama-3-70b-hf", "Qwen/Qwen2.5-72B-Instruct", "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference", "meta-llama/Llama-3.2-1B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference", "meta-llama/Meta-Llama-3-8B-Instruct", "meta-llama/Llama-3.1-405B-Instruct", "cartesia/sonic", "cartesia/sonic-2", "togethercomputer/MoA-1", "Salesforce/Llama-Rank-V1", "black-forest-labs/FLUX.1-schnell", "lgai/exaone-3-5-32b-instruct", "lgai/exaone-deep-32b", "black-forest-labs/FLUX.1-dev", "marin-community/marin-8b-instruct", "togethercomputer/Refuel-Llm-V2-Small", "meta-llama/Llama-3-70b-chat-hf", "Alibaba-NLP/gte-modernbert-base", "black-forest-labs/FLUX.1-pro", "black-forest-labs/FLUX.1.1-pro", "togethercomputer/MoA-1-Turbo", "black-forest-labs/FLUX.1-dev-lora", "meta-llama/Llama-2-70b-hf", "togethercomputer/m2-bert-80M-32k-retrieval", "togethercomputer/Refuel-Llm-V2", "intfloat/multilingual-e5-large-instruct", "black-forest-labs/FLUX.1-kontext-max", "black-forest-labs/FLUX.1-schnell-Free", "black-forest-labs/FLUX.1-kontext-pro", "BAAI/bge-large-en-v1.5", "BAAI/bge-base-en-v1.5", "Qwen/Qwen3-Next-80B-A3B-Instruct", "ServiceNow-AI/Apriel-1.5-15b-Thinker", "openai/whisper-large-v3-test", "codellama/CodeLlama-34b-Instruct-hf", "meta-llama/Llama-2-13b-chat-hf", "togethercomputer/m2-bert-80M-8k-retrieval", "WhereIsAI/UAE-Large-V1", "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro", "togethercomputer/m2-bert-80M-2k-retrieval", "meta-llama/Meta-Llama-3-70B-Instruct-Lite", "Meta-Llama/Llama-Guard-7b", "Gryphe/MythoMax-L2-13b-Lite", "upstage/SOLAR-10.7B-Instruct-v1.0", "Qwen/Qwen2.5-14B-Instruct", "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free", "zai-org/GLM-4.5-Air-FP8", "kwaivgI/kling-1.6-standard", "HiDream-ai/HiDream-I1-Full", "ByteDance-Seed/Seedream-3.0", "ByteDance-Seed/Seedream-4.0", "Lykon/DreamShaper", "HiDream-ai/HiDream-I1-Dev", "Qwen/Qwen-Image", "RunDiffusion/Juggernaut-pro-flux", "google/imagen-4.0-preview", "google/imagen-4.0-ultra", "google/veo-3.0", "minimax/hailuo-02", "stabilityai/stable-diffusion-3-medium", "black-forest-labs/FLUX.1-Canny-pro", "google/imagen-4.0-fast", "minimax/video-01-director", "HiDream-ai/HiDream-I1-Fast", "Wan-AI/Wan2.2-T2V-A14B", "ByteDance/Seedance-1.0-pro", "google/veo-3.0-fast-audio", "vidu/vidu-q1", "kwaivgI/kling-2.1-master", "google/veo-3.0-audio", "Rundiffusion/Juggernaut-Lightning-Flux", "Wan-AI/Wan2.2-I2V-A14B", "google/flash-image-2.5", "google/veo-2.0", "openai/sora-2", "google/veo-3.0-fast", "ideogram/ideogram-3.0", "kwaivgI/kling-2.0-master", "kwaivgI/kling-2.1-standard", "pixverse/pixverse-v5", "stabilityai/stable-diffusion-xl-base-1.0", "openai/sora-2-pro", "ByteDance/Seedance-1.0-lite", "kwaivgI/kling-1.6-pro", "vidu/vidu-2.0", "kwaivgI/kling-2.1-pro", "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "canopylabs/orpheus-3b-0.1-ft", "hexgrad/Kokoro-82M", "eddie/gemma-2b-it", "mistralai/Voxtral-Mini-3B-2507", "arcee-ai/coder-large", "arcee-ai/virtuoso-large", "arcee-ai/maestro-reasoning", "deepcogito/cogito-v2-1-671b", "arcee_ai/arcee-spotlight", "google/gemini-3-pro-image", "mercor/cwm", "black-forest-labs/FLUX.2-flex", "keith-aditya/kimi-k2-instruct", "pangram/mistral-small-2501", "black-forest-labs/FLUX.2-pro", "black-forest-labs/FLUX.2-dev", "ServiceNow-AI/Apriel-1.6-15b-Thinker" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Together", "provider_slug": "together", "provider_model_id": "deepcogito/cogito-v2-preview-llama-109B-MoE", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "top_k", "repetition_penalty", "logit_bias", "min_p", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "pricing": { "prompt": "0.00000018", "completion": "0.00000059", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000018", "openai:completion_tokens": "0.00000059" }, "pricing_version_id": "bf29ccf8-e7d6-4fed-8e34-100d2a2172c4", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": "2026-02-04" } }, { "slug": "stepfun-ai/step3", "hf_slug": "stepfun-ai/step3", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-28T21:09:35.282323+00:00", "hf_updated_at": null, "name": "StepFun: Step3", "short_name": "Step3", "author": "stepfun-ai", "description": "Step3 is a cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators.", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "stepfun-ai/step3", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d07c4675-6f77-4783-b2ab-2123a5064d2c", "name": "SiliconFlow | stepfun-ai/step3", "context_length": 65536, "model": { "slug": "stepfun-ai/step3", "hf_slug": "stepfun-ai/step3", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-28T21:09:35.282323+00:00", "hf_updated_at": null, "name": "StepFun: Step3", "short_name": "Step3", "author": "stepfun-ai", "description": "Step3 is a cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators.", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "stepfun-ai/step3", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "stepfun-ai/step3", "model_variant_permaslug": "stepfun-ai/step3", "adapter_name": "SiliconFlowAdapter", "provider_name": "SiliconFlow", "provider_info": { "name": "SiliconFlow", "displayName": "SiliconFlow", "slug": "siliconflow", "baseUrl": "https://api.siliconflow.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "headquarters": "SG", "datacenters": [], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "SiliconFlowAdapter", "isMultipartSupported": false, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "/images/icons/SiliconFlow.svg" }, "ignoredProviderModels": [ "inclusionAI/Ling-mini-2.0", "inclusionAI/Ring-flash-2.0", "inclusionAI/Ling-flash-2.0" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "SiliconFlow", "provider_slug": "siliconflow/fp8", "provider_model_id": "stepfun-ai/step3", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65536, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "temperature", "top_p", "top_k", "frequency_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://docs.siliconflow.com/en/legals/terms-of-service", "privacyPolicyURL": "https://docs.siliconflow.com/en/legals/privacy-policy" }, "pricing": { "prompt": "0.00000057", "completion": "0.00000142", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000057", "openai:completion_tokens": "0.00000142" }, "pricing_version_id": "691bbba1-c72e-4d5a-85f4-89fe9fe29f3b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-medium-3.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-13T14:33:59.459114+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Medium 3.1", "short_name": "Mistral Medium 3.1", "author": "mistralai", "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-medium-3.1", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "13c5002b-8c5b-490c-8a5f-52ec0242804f", "name": "Mistral | mistralai/mistral-medium-3.1", "context_length": 131072, "model": { "slug": "mistralai/mistral-medium-3.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-13T14:33:59.459114+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Medium 3.1", "short_name": "Mistral Medium 3.1", "author": "mistralai", "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-medium-3.1", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-medium-3.1", "model_variant_permaslug": "mistralai/mistral-medium-3.1", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "mistral-medium-2508", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.0000004", "completion": "0.000002", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 4e-7, "mistral:completion_tokens": 0.000002 }, "pricing_version_id": "2fd2a6a7-7579-4e66-88b2-3ff4e4d7e68d", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "baidu/ernie-4.5-vl-28b-a3b", "hf_slug": "baidu/ERNIE-4.5-VL-28B-A3B-PT", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-12T21:07:16.565993+00:00", "hf_updated_at": null, "name": "Baidu: ERNIE 4.5 VL 28B A3B", "short_name": "ERNIE 4.5 VL 28B A3B", "author": "baidu", "description": "A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing. Built with scaling-efficient infrastructure for high-throughput training and inference, the model leverages advanced post-training techniques including SFT, DPO, and UPO for optimized performance, while supporting an impressive 131K context length and RLVR alignment for superior cross-modal reasoning and generation capabilities.", "model_version_group_id": null, "context_length": 30000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "baidu/ernie-4.5-vl-28b-a3b", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "75e64609-6b51-4e35-96ea-5065c6fbda63", "name": "Novita | baidu/ernie-4.5-vl-28b-a3b", "context_length": 30000, "model": { "slug": "baidu/ernie-4.5-vl-28b-a3b", "hf_slug": "baidu/ERNIE-4.5-VL-28B-A3B-PT", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-12T21:07:16.565993+00:00", "hf_updated_at": null, "name": "Baidu: ERNIE 4.5 VL 28B A3B", "short_name": "ERNIE 4.5 VL 28B A3B", "author": "baidu", "description": "A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing. Built with scaling-efficient infrastructure for high-throughput training and inference, the model leverages advanced post-training techniques including SFT, DPO, and UPO for optimized performance, while supporting an impressive 131K context length and RLVR alignment for superior cross-modal reasoning and generation capabilities.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "baidu/ernie-4.5-vl-28b-a3b", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "baidu/ernie-4.5-vl-28b-a3b", "model_variant_permaslug": "baidu/ernie-4.5-vl-28b-a3b", "adapter_name": "NovitaAdapter", "provider_name": "Novita", "provider_info": { "name": "Novita", "displayName": "NovitaAI", "slug": "novita", "baseUrl": "https://api.novita.ai/v3/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P2zP0TCZwbzCC8QkH8m8o1i8M" ], "adapterName": "NovitaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.novita.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256" }, "ignoredProviderModels": [ "google/gemma-3-1b-it", "baichuan/baichuan-m2-32b", "baidu/ernie-4.5-0.3b", "qwen/qwen-mt-plus", "qwen/qwen3-4b-fp8", "meta-llama/llama-3.2-1b-instruct", "sophosympatheia/midnight-rose-70b", "deepseek/deepseek-prover-v2-671b", "Sao10K/L3-8B-Stheno-v3.2", "thudm/glm-4-32b-0414", "qwen/qwen3-omni-30b-a3b-thinking", "qwen/qwen3-omni-30b-a3b-instruct", "paddlepaddle/paddleocr-vl", "deepseek/deepseek-ocr", "skywork/r1v4-lite", "baidu/ernie-4.5-vl-28b-a3b-thinking", "zai-org/autoglm-phone-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NovitaAI", "provider_slug": "novita/fp16", "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b", "quantization": "fp16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 8000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "pricing": { "prompt": "0.00000014", "completion": "0.00000056", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000014", "openai:completion_tokens": "0.00000056" }, "pricing_version_id": "2b814f58-4fa0-4308-ae26-03d5ed15732f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "z-ai/glm-4.5v", "hf_slug": "zai-org/GLM-4.5V", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-11T14:24:48.340676+00:00", "hf_updated_at": null, "name": "Z.AI: GLM 4.5V", "short_name": "GLM 4.5V", "author": "z-ai", "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "z-ai/glm-4.5v", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null } }, "default_parameters": { "temperature": 0.75, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "30f10717-f218-430f-a3d7-858bf5fdf303", "name": "Novita | z-ai/glm-4.5v", "context_length": 65536, "model": { "slug": "z-ai/glm-4.5v", "hf_slug": "zai-org/GLM-4.5V", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-11T14:24:48.340676+00:00", "hf_updated_at": null, "name": "Z.AI: GLM 4.5V", "short_name": "GLM 4.5V", "author": "z-ai", "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "z-ai/glm-4.5v", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null } }, "default_parameters": { "temperature": 0.75, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "z-ai/glm-4.5v", "model_variant_permaslug": "z-ai/glm-4.5v", "adapter_name": "NovitaAdapter", "provider_name": "Novita", "provider_info": { "name": "Novita", "displayName": "NovitaAI", "slug": "novita", "baseUrl": "https://api.novita.ai/v3/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P2zP0TCZwbzCC8QkH8m8o1i8M" ], "adapterName": "NovitaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.novita.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256" }, "ignoredProviderModels": [ "google/gemma-3-1b-it", "baichuan/baichuan-m2-32b", "baidu/ernie-4.5-0.3b", "qwen/qwen-mt-plus", "qwen/qwen3-4b-fp8", "meta-llama/llama-3.2-1b-instruct", "sophosympatheia/midnight-rose-70b", "deepseek/deepseek-prover-v2-671b", "Sao10K/L3-8B-Stheno-v3.2", "thudm/glm-4-32b-0414", "qwen/qwen3-omni-30b-a3b-thinking", "qwen/qwen3-omni-30b-a3b-instruct", "paddlepaddle/paddleocr-vl", "deepseek/deepseek-ocr", "skywork/r1v4-lite", "baidu/ernie-4.5-vl-28b-a3b-thinking", "zai-org/autoglm-phone-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NovitaAI", "provider_slug": "novita/fp8", "provider_model_id": "zai-org/glm-4.5v", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "pricing": { "prompt": "0.0000006", "completion": "0.0000018", "image": "0", "request": "0", "input_cache_read": "0.00000011", "input_cache_write": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000006", "openai:completion_tokens": "0.0000018", "openai:cached_prompt_tokens": "0.00000011" }, "pricing_version_id": "e6847a35-8151-4bb4-893d-caa884086509", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-chat", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-07T17:30:37.42514+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Chat", "short_name": "GPT-5 Chat", "author": "openai", "description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-chat-2025-08-07", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "8f8398f5-523f-4676-8ba4-e82e3484efb1", "name": "OpenAI | openai/gpt-5-chat-2025-08-07", "context_length": 128000, "model": { "slug": "openai/gpt-5-chat", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-07T17:30:37.42514+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Chat", "short_name": "GPT-5 Chat", "author": "openai", "description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-chat-2025-08-07", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-chat", "model_variant_permaslug": "openai/gpt-5-chat-2025-08-07", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-chat-latest", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "structured_outputs", "response_format", "seed", "max_tokens" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "3895cfdc-b31b-4b8e-b29a-e5b9d384a71e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:33+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5", "short_name": "GPT-5", "author": "openai", "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "openai/discounted", "openai/default", "azure" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "7c2f859a-7890-4e8e-b1de-1cd1c0a800b4", "name": "OpenAI | openai/gpt-5-2025-08-07", "context_length": 400000, "model": { "slug": "openai/gpt-5", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:33+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5", "short_name": "GPT-5", "author": "openai", "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": null, "permaslug": "openai/gpt-5-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "openai/discounted", "openai/default", "azure" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5", "model_variant_permaslug": "openai/gpt-5-2025-08-07", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai/default", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai/default", "provider_model_id": "gpt-5-2025-08-07", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "input_cache_read": "0.000000125", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00000125, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00001, "openai_responses:cached_prompt_tokens": 1.25e-7 }, "pricing_version_id": "c6d64142-2e88-4d34-8469-6b1dd34b407a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-mini", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:27+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Mini", "short_name": "GPT-5 Mini", "author": "openai", "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-mini-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "c4f66d01-20b0-4c27-a225-438ea22fda43", "name": "OpenAI | openai/gpt-5-mini-2025-08-07", "context_length": 400000, "model": { "slug": "openai/gpt-5-mini", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:27+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Mini", "short_name": "GPT-5 Mini", "author": "openai", "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-mini-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-mini", "model_variant_permaslug": "openai/gpt-5-mini-2025-08-07", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-mini-2025-08-07", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000025", "completion": "0.000002", "input_cache_read": "0.000000025", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 2.5e-7, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000002, "openai_responses:cached_prompt_tokens": 2.5e-8 }, "pricing_version_id": "e3e873c5-5dc5-476b-9720-a23c7d318945", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-5-nano", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:22+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Nano", "short_name": "GPT-5 Nano", "author": "openai", "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-nano-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "50329d77-04e1-4979-a184-c33030289476", "name": "OpenAI | openai/gpt-5-nano-2025-08-07", "context_length": 400000, "model": { "slug": "openai/gpt-5-nano", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-08-07T17:23:22+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-5 Nano", "short_name": "GPT-5 Nano", "author": "openai", "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.", "model_version_group_id": null, "context_length": 400000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-5-nano-2025-08-07", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-5-nano", "model_variant_permaslug": "openai/gpt-5-nano-2025-08-07", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-5-nano-2025-08-07", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": 272000, "max_completion_tokens": 128000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000005", "completion": "0.0000004", "input_cache_read": "0.000000005", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 5e-8, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 4e-7, "openai_responses:cached_prompt_tokens": 5e-9 }, "pricing_version_id": "ea868e66-5993-4315-9540-a5f7cd5d9d07", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_implicit_caching": true, "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-opus-4.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-05T16:33:11.634562+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4.1", "short_name": "Claude Opus 4.1", "author": "anthropic", "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4.1-opus-20250805", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ece5c3c6-e437-4297-92fc-150a1771ec56", "name": "Amazon Bedrock | anthropic/claude-4.1-opus-20250805", "context_length": 200000, "model": { "slug": "anthropic/claude-opus-4.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-05T16:33:11.634562+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4.1", "short_name": "Claude Opus 4.1", "author": "anthropic", "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4.1-opus-20250805", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-opus-4.1", "model_variant_permaslug": "anthropic/claude-4.1-opus-20250805", "adapter_name": "AmazonBedrockInvokeAnthropicAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.anthropic.claude-opus-4-1-20250805-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.000015", "completion": "0.000075", "input_cache_read": "0.0000015", "input_cache_write": "0.00001875", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000015, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 0.0000015, "anthropic:completion_tokens": 0.000075, "anthropic:cache_write_1h_tokens": 0.00003, "anthropic:cache_write_5m_tokens": 0.00001875 }, "pricing_version_id": "ce33ad08-2e47-4675-9bac-0d5dbf2173f3", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "bytedance/ui-tars-1.5-7b", "hf_slug": "ByteDance-Seed/UI-TARS-1.5-7B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-22T17:24:16.94785+00:00", "hf_updated_at": null, "name": "ByteDance: UI-TARS 7B ", "short_name": "UI-TARS 7B ", "author": "bytedance", "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces.\n\nThis model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "bytedance/ui-tars-1.5-7b", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "22a474a1-cb4e-42d2-b19a-c1be103f5abd", "name": "Parasail | bytedance/ui-tars-1.5-7b", "context_length": 128000, "model": { "slug": "bytedance/ui-tars-1.5-7b", "hf_slug": "ByteDance-Seed/UI-TARS-1.5-7B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-22T17:24:16.94785+00:00", "hf_updated_at": null, "name": "ByteDance: UI-TARS 7B ", "short_name": "UI-TARS 7B ", "author": "bytedance", "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces.\n\nThis model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "bytedance/ui-tars-1.5-7b", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "bytedance/ui-tars-1.5-7b", "model_variant_permaslug": "bytedance/ui-tars-1.5-7b", "adapter_name": "ParasailAdapter", "provider_name": "Parasail", "provider_info": { "name": "Parasail", "displayName": "Parasail", "slug": "parasail", "baseUrl": "https://api.parasail.io/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.parasail.io/legal/terms", "privacyPolicyURL": "https://www.parasail.io/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P5Ca01in28Ek1oxb5OtfZdEjQ", "user_37qaJKhqfUEFgVF46sarwDHxE50" ], "adapterName": "ParasailAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256" }, "ignoredProviderModels": [ "parasail-olmo-2-1124-7b-instruct", "parasail-qwen3-omni-30b-a3b-thinking", "parasail-qwen3-omni-30b-a3b-instruct", "parasail-dots-ocr", "parasail-auto-glm-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Parasail", "provider_slug": "parasail/bf16", "provider_model_id": "parasail-ui-tars-1p5-7b", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 2048, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "frequency_penalty", "presence_penalty", "repetition_penalty", "seed", "stop", "top_k", "logit_bias" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.parasail.io/legal/terms", "privacyPolicyURL": "https://www.parasail.io/legal/privacy-policy" }, "pricing": { "prompt": "0.0000001", "completion": "0.0000002", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000001", "openai:completion_tokens": "0.0000002" }, "pricing_version_id": "1b8708ef-a746-47f0-9c63-2fb0a1367dab", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-flash-lite", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-22T16:04:36.283638+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Lite", "short_name": "Gemini 2.5 Flash Lite", "author": "google", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-lite", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ebdbef25-737d-4ac3-9e98-fd3928724e45", "name": "Google | google/gemini-2.5-flash-lite", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-flash-lite", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-22T16:04:36.283638+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Lite", "short_name": "Gemini 2.5 Flash Lite", "author": "google", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-lite", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-flash-lite", "model_variant_permaslug": "google/gemini-2.5-flash-lite", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.5-flash-lite", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000001", "completion": "0.0000004", "image": "0.0000001", "audio": "0.0000003", "input_audio_cache": "0.00000003", "input_cache_read": "0.00000001", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000004", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 1e-7, "gemini:reasoning_tokens": 4e-7, "gemini:cache_read_tokens": 1e-8, "gemini:completion_tokens": 4e-7, "gemini:text_input_tokens": 1e-7, "gemini:audio_input_tokens": 3e-7, "gemini:image_input_tokens": 1e-7, "gemini:video_input_tokens": 1e-7, "gemini:cache_read_text_tokens": 1e-8, "gemini:cache_read_audio_tokens": 3e-8, "gemini:cache_read_image_tokens": 1e-8, "gemini:cache_read_video_tokens": 1e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 3e-8, "gemini:cache_read_text_tokens_high_context": 3e-8, "gemini:cache_read_audio_tokens_high_context": 6e-8, "gemini:cache_read_image_tokens_high_context": 3e-8, "gemini:cache_read_video_tokens_high_context": 3e-8, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "ca89601f-77de-41b0-b355-c79b0503e789", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "x-ai/grok-4", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-07-09T19:01:29.595463+00:00", "hf_updated_at": null, "name": "xAI: Grok 4", "short_name": "Grok 4", "author": "x-ai", "description": "Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the [xAI docs](https://docs.x.ai/docs/models/grok-4-0709)", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "x-ai/grok-4-07-09", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d40bef9d-6936-4c57-9749-bf7399de4a77", "name": "xAI | x-ai/grok-4-07-09", "context_length": 256000, "model": { "slug": "x-ai/grok-4", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-07-09T19:01:29.595463+00:00", "hf_updated_at": null, "name": "xAI: Grok 4", "short_name": "Grok 4", "author": "x-ai", "description": "Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the [xAI docs](https://docs.x.ai/docs/models/grok-4-0709)", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "x-ai/grok-4-07-09", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "x-ai/grok-4", "model_variant_permaslug": "x-ai/grok-4-07-09", "adapter_name": "XAIResponsesAdapter", "provider_name": "xAI", "provider_info": { "name": "xAI", "displayName": "xAI", "slug": "xai", "baseUrl": "https://api.x.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "XAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.x.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "xAI", "provider_slug": "xai", "provider_model_id": "grok-4-0709", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "max_tokens", "temperature", "top_p", "seed", "logprobs", "top_logprobs", "response_format", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://x.ai/legal/terms-of-service-enterprise", "privacyPolicyURL": "https://x.ai/legal/privacy-policy", "requiresUserIDs": true }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "image": "0", "request": "0", "input_cache_read": "0.00000075", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 128000, "prompt": "0.000006", "completions": "0.00003", "input_cache_read": "0.00000075" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "baidu/ernie-4.5-vl-424b-a47b", "hf_slug": "baidu/ERNIE-4.5-VL-424B-A47B-PT", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-30T16:28:23.022047+00:00", "hf_updated_at": null, "name": "Baidu: ERNIE 4.5 VL 424B A47B ", "short_name": "ERNIE 4.5 VL 424B A47B ", "author": "baidu", "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.", "model_version_group_id": null, "context_length": 123000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "baidu/ernie-4.5-vl-424b-a47b", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "1fe59382-263d-4107-a768-d7d2007bd3b6", "name": "Novita | baidu/ernie-4.5-vl-424b-a47b", "context_length": 123000, "model": { "slug": "baidu/ernie-4.5-vl-424b-a47b", "hf_slug": "baidu/ERNIE-4.5-VL-424B-A47B-PT", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-30T16:28:23.022047+00:00", "hf_updated_at": null, "name": "Baidu: ERNIE 4.5 VL 424B A47B ", "short_name": "ERNIE 4.5 VL 424B A47B ", "author": "baidu", "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "baidu/ernie-4.5-vl-424b-a47b", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "baidu/ernie-4.5-vl-424b-a47b", "model_variant_permaslug": "baidu/ernie-4.5-vl-424b-a47b", "adapter_name": "NovitaAdapter", "provider_name": "Novita", "provider_info": { "name": "Novita", "displayName": "NovitaAI", "slug": "novita", "baseUrl": "https://api.novita.ai/v3/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "org_34P2zP0TCZwbzCC8QkH8m8o1i8M" ], "adapterName": "NovitaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.novita.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256" }, "ignoredProviderModels": [ "google/gemma-3-1b-it", "baichuan/baichuan-m2-32b", "baidu/ernie-4.5-0.3b", "qwen/qwen-mt-plus", "qwen/qwen3-4b-fp8", "meta-llama/llama-3.2-1b-instruct", "sophosympatheia/midnight-rose-70b", "deepseek/deepseek-prover-v2-671b", "Sao10K/L3-8B-Stheno-v3.2", "thudm/glm-4-32b-0414", "qwen/qwen3-omni-30b-a3b-thinking", "qwen/qwen3-omni-30b-a3b-instruct", "paddlepaddle/paddleocr-vl", "deepseek/deepseek-ocr", "skywork/r1v4-lite", "baidu/ernie-4.5-vl-28b-a3b-thinking", "zai-org/autoglm-phone-9b-multilingual" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "NovitaAI", "provider_slug": "novita/fp16", "provider_model_id": "baidu/ernie-4.5-vl-424b-a47b", "quantization": "fp16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://novita.ai/legal/terms-of-service", "privacyPolicyURL": "https://novita.ai/legal/privacy-policy" }, "pricing": { "prompt": "0.00000042", "completion": "0.00000125", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000042", "openai:completion_tokens": "0.00000125" }, "pricing_version_id": "e58a9bae-ceb6-44a8-be53-c128c4e5511c", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": false, "structured_outputs": false }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-small-3.2-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-20T18:10:16.960494+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.2 24B", "short_name": "Mistral Small 3.2 24B", "author": "mistralai", "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.2-24b-instruct-2506", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "a19c2a4a-f3dc-451f-ae9f-07ae51a6b234", "name": "Chutes | mistralai/mistral-small-3.2-24b-instruct-2506", "context_length": 131072, "model": { "slug": "mistralai/mistral-small-3.2-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-20T18:10:16.960494+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.2 24B", "short_name": "Mistral Small 3.2 24B", "author": "mistralai", "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.2-24b-instruct-2506", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-small-3.2-24b-instruct", "model_variant_permaslug": "mistralai/mistral-small-3.2-24b-instruct-2506", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "chutesai/Mistral-Small-3.2-24B-Instruct-2506", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 131072, "max_tokens_per_image": null, "supported_parameters": [ "structured_outputs", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000006", "completion": "0.00000018", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000006", "openai:completion_tokens": "0.00000018" }, "pricing_version_id": "1d6d5961-adba-4451-802e-a5184f1d881a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-flash", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-17T15:01:28.103313+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash", "short_name": "Gemini 2.5 Flash", "author": "google", "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "file", "image", "text", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-flash", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "b9b095f0-6448-46bb-8e4c-0111ba2bf1b0", "name": "Google | google/gemini-2.5-flash", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-flash", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-06-17T15:01:28.103313+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash", "short_name": "Gemini 2.5 Flash", "author": "google", "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "file", "image", "text", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-flash", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-flash", "model_variant_permaslug": "google/gemini-2.5-flash", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex (Global)", "slug": "google-vertex/global", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex (Global)", "provider_slug": "google-vertex/global", "provider_model_id": "gemini-2.5-flash", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000003", "completion": "0.0000025", "image": "0.0000003", "audio": "0.000001", "input_audio_cache": "0.0000001", "input_cache_read": "0.00000003", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000025", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 3e-7, "gemini:reasoning_tokens": 0.0000025, "gemini:cache_read_tokens": 3e-8, "gemini:completion_tokens": 0.0000025, "gemini:text_input_tokens": 3e-7, "gemini:audio_input_tokens": 0.000001, "gemini:image_input_tokens": 3e-7, "gemini:video_input_tokens": 3e-7, "gemini:cache_read_text_tokens": 3e-8, "gemini:cache_read_audio_tokens": 1e-7, "gemini:cache_read_image_tokens": 3e-8, "gemini:cache_read_video_tokens": 3e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 1e-7, "gemini:cache_read_text_tokens_high_context": 1e-7, "gemini:cache_read_audio_tokens_high_context": 2e-7, "gemini:cache_read_image_tokens_high_context": 1e-7, "gemini:cache_read_video_tokens_high_context": 1e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "797f6b33-5ecc-4010-bdf0-d1db8d4d4c00", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "supports_input_audio": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "google/gemini-2.5-pro", "hf_slug": "", "updated_at": "2026-01-08T23:55:54.79011+00:00", "created_at": "2025-06-17T14:12:24+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro", "short_name": "Gemini 2.5 Pro", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "43106252-bd69-498f-84f5-1fde678783f7", "name": "Google | google/gemini-2.5-pro", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-pro", "hf_slug": "", "updated_at": "2026-01-08T23:55:54.79011+00:00", "created_at": "2025-06-17T14:12:24+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro", "short_name": "Gemini 2.5 Pro", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null, "default_reasoning_enabled": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_max_tokens": null, "supported_reasoning_efforts": null, "default_reasoning_effort": null, "default_reasoning_enabled": null }, "chat_template_config": { "should_hoist_and_merge_system_messages": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-pro", "model_variant_permaslug": "google/gemini-2.5-pro", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex (Global)", "slug": "google-vertex/global", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex (Global)", "provider_slug": "google-vertex/global", "provider_model_id": "gemini-2.5-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65536, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "image": "0.00000125", "audio": "0.00000125", "input_audio_cache": "0.000000125", "input_cache_read": "0.000000125", "input_cache_write": "0.000000375", "internal_reasoning": "0.00001", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.0000025", "completions": "0.000015", "input_cache_read": "0.00000025", "input_cache_write": "0.00000075" } ], "pricing_json": { "gemini:prompt_tokens": 0.00000125, "gemini:reasoning_tokens": 0.00001, "gemini:cache_read_tokens": 1.25e-7, "gemini:completion_tokens": 0.00001, "gemini:text_input_tokens": 0.00000125, "gemini:audio_input_tokens": 0.00000125, "gemini:image_input_tokens": 0.00000125, "gemini:video_input_tokens": 0.00000125, "gemini:cache_read_text_tokens": 1.25e-7, "gemini:cache_read_audio_tokens": 1.25e-7, "gemini:cache_read_image_tokens": 1.25e-7, "gemini:cache_read_video_tokens": 1.25e-7, "gemini:cache_write_storage_hours": 0.0000045, "gemini:prompt_tokens_high_context": 0.0000025, "gemini:reasoning_tokens_high_context": 0.000015, "gemini:cache_read_tokens_high_context": 2.5e-7, "gemini:completion_tokens_high_context": 0.000015, "gemini:cache_read_text_tokens_high_context": 2.5e-7, "gemini:cache_read_audio_tokens_high_context": 2.5e-7, "gemini:cache_read_image_tokens_high_context": 2.5e-7, "gemini:cache_read_video_tokens_high_context": 2.5e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "30d9e9ac-2660-46f4-8467-957c8615eb9a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": 300, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true, "supports_input_audio": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "openai/o3-pro", "hf_slug": "", "updated_at": "2026-01-14T02:46:50.629344+00:00", "created_at": "2025-06-10T23:32:32.266087+00:00", "hf_updated_at": null, "name": "OpenAI: o3 Pro", "short_name": "o3 Pro", "author": "openai", "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "file", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o3-pro-2025-06-10", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "b8222376-66ee-4b89-a7c9-e627ba35db79", "name": "OpenAI | openai/o3-pro-2025-06-10", "context_length": 200000, "model": { "slug": "openai/o3-pro", "hf_slug": "", "updated_at": "2026-01-14T02:46:50.629344+00:00", "created_at": "2025-06-10T23:32:32.266087+00:00", "hf_updated_at": null, "name": "OpenAI: o3 Pro", "short_name": "o3 Pro", "author": "openai", "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "file", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o3-pro-2025-06-10", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o3-pro", "model_variant_permaslug": "openai/o3-pro-2025-06-10", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o3-pro-2025-06-10", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00002", "completion": "0.00008", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00002, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.00008 }, "pricing_version_id": "1f6bd1f8-e039-4a39-818c-0c098678cc9b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-pro-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-06-05T15:27:37.538116+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro Preview 06-05", "short_name": "Gemini 2.5 Pro Preview 06-05", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.\n", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "file", "image", "text", "audio" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro-preview-06-05", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "018040ae-9cda-43cd-8813-d8ca83f6c7ed", "name": "Google | google/gemini-2.5-pro-preview-06-05", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-pro-preview", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-06-05T15:27:37.538116+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro Preview 06-05", "short_name": "Gemini 2.5 Pro Preview 06-05", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.\n", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "file", "image", "text", "audio" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro-preview-06-05", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-pro-preview", "model_variant_permaslug": "google/gemini-2.5-pro-preview-06-05", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.5-pro-preview-06-05", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65536, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "image": "0.00000125", "audio": "0.00000125", "input_audio_cache": "0.000000125", "input_cache_read": "0.000000125", "input_cache_write": "0.000000375", "internal_reasoning": "0.00001", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.0000025", "completions": "0.000015", "input_cache_read": "0.000000625", "input_cache_write": "0.00000075" } ], "pricing_json": { "gemini:prompt_tokens": 0.00000125, "gemini:reasoning_tokens": 0.00001, "gemini:cache_read_tokens": 1.25e-7, "gemini:completion_tokens": 0.00001, "gemini:text_input_tokens": 0.00000125, "gemini:audio_input_tokens": 0.00000125, "gemini:image_input_tokens": 0.00000125, "gemini:video_input_tokens": 0.00000125, "gemini:cache_read_text_tokens": 1.25e-7, "gemini:cache_read_audio_tokens": 1.25e-7, "gemini:cache_read_image_tokens": 1.25e-7, "gemini:cache_read_video_tokens": 1.25e-7, "gemini:cache_write_storage_hours": 0.0000045, "gemini:prompt_tokens_high_context": 0.0000025, "gemini:reasoning_tokens_high_context": 0.000015, "gemini:cache_read_tokens_high_context": 2.5e-7, "gemini:completion_tokens_high_context": 0.000015, "gemini:cache_read_text_tokens_high_context": 2.5e-7, "gemini:cache_read_audio_tokens_high_context": 2.5e-7, "gemini:cache_read_image_tokens_high_context": 2.5e-7, "gemini:cache_read_video_tokens_high_context": 2.5e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "5e816caa-530e-4a3d-be95-5a26323e7b48", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": "global", "deprecation_date": null } }, { "slug": "anthropic/claude-opus-4", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-22T16:27:25.029961+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4", "short_name": "Claude Opus 4", "author": "anthropic", "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4-opus-20250522", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "a1d11e23-4e05-42cf-9fa3-6cacdb8d384a", "name": "Amazon Bedrock | anthropic/claude-4-opus-20250522", "context_length": 200000, "model": { "slug": "anthropic/claude-opus-4", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-22T16:27:25.029961+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Opus 4", "short_name": "Claude Opus 4", "author": "anthropic", "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4-opus-20250522", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-opus-4", "model_variant_permaslug": "anthropic/claude-4-opus-20250522", "adapter_name": "AmazonBedrockInvokeAnthropicAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.anthropic.claude-opus-4-20250514-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 32000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.000015", "completion": "0.000075", "input_cache_read": "0.0000015", "input_cache_write": "0.00001875", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000015, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 0.0000015, "anthropic:completion_tokens": 0.000075, "anthropic:cache_write_1h_tokens": 0.00003, "anthropic:cache_write_5m_tokens": 0.00001875 }, "pricing_version_id": "20a35276-23ac-4521-a7cb-ef4e84ed336e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-sonnet-4", "hf_slug": "", "updated_at": "2025-12-05T21:53:41.372783+00:00", "created_at": "2025-05-22T16:12:51.381897+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Sonnet 4", "short_name": "Claude Sonnet 4", "author": "anthropic", "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4-sonnet-20250522", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "5e3f0568-c089-416a-ab7b-6c432999b571", "name": "Google | anthropic/claude-4-sonnet-20250522", "context_length": 1000000, "model": { "slug": "anthropic/claude-sonnet-4", "hf_slug": "", "updated_at": "2025-12-05T21:53:41.372783+00:00", "created_at": "2025-05-22T16:12:51.381897+00:00", "hf_updated_at": null, "name": "Anthropic: Claude Sonnet 4", "short_name": "Claude Sonnet 4", "author": "anthropic", "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-4-sonnet-20250522", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-sonnet-4", "model_variant_permaslug": "anthropic/claude-4-sonnet-20250522", "adapter_name": "GoogleVertexAnthropicAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "claude-sonnet-4@20250514", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "top_p", "temperature", "stop", "reasoning", "include_reasoning", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "input_cache_read": "0.0000003", "input_cache_write": "0.00000375", "web_search": "0.01", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.000006", "completions": "0.0000225", "input_cache_read": "0.0000006", "input_cache_write": "0.0000075" } ], "pricing_json": { "anthropic:prompt_tokens": 0.000003, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 3e-7, "anthropic:completion_tokens": 0.000015, "anthropic:cache_write_1h_tokens": 0.000006, "anthropic:cache_write_5m_tokens": 0.00000375, "anthropic:long_context_threshold": 200000, "anthropic:prompt_tokens_long_context": 0.000006, "anthropic:cache_read_tokens_long_context": 6e-7, "anthropic:completion_tokens_long_context": 0.0000225, "anthropic:cache_write_1h_tokens_long_context": 0.000012, "anthropic:cache_write_5m_tokens_long_context": 0.0000075 }, "pricing_version_id": "7a5a3265-459b-49f7-9a79-938da5dd2363", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-medium-3", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-07T14:15:41.980763+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Medium 3", "short_name": "Mistral Medium 3", "author": "mistralai", "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-medium-3", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "9d5ba5bf-8465-46df-9185-1330820338f5", "name": "Mistral | mistralai/mistral-medium-3", "context_length": 131072, "model": { "slug": "mistralai/mistral-medium-3", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-07T14:15:41.980763+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Medium 3", "short_name": "Mistral Medium 3", "author": "mistralai", "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-medium-3", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-medium-3", "model_variant_permaslug": "mistralai/mistral-medium-3", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "mistral-medium-2505", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.0000004", "completion": "0.000002", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 4e-7, "mistral:completion_tokens": 0.000002 }, "pricing_version_id": "25450ac1-aa83-42d4-b87b-3a37014630c6", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.5-pro-preview-05-06", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-05-07T00:41:53+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro Preview 05-06", "short_name": "Gemini 2.5 Pro Preview 05-06", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro-preview-03-25", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "9d2cac4d-81d4-4e67-ac7a-6c73040655ee", "name": "Google | google/gemini-2.5-pro-preview-03-25", "context_length": 1048576, "model": { "slug": "google/gemini-2.5-pro-preview-05-06", "hf_slug": "", "updated_at": "2026-01-08T19:23:52.555156+00:00", "created_at": "2025-05-07T00:41:53+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro Preview 05-06", "short_name": "Gemini 2.5 Pro Preview 05-06", "author": "google", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro-preview-03-25", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.5-pro-preview-05-06", "model_variant_permaslug": "google/gemini-2.5-pro-preview-03-25", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.5-pro-preview-05-06", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 65535, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "seed", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000125", "completion": "0.00001", "image": "0.00000125", "audio": "0.00000125", "input_audio_cache": "0.000000125", "input_cache_read": "0.000000125", "input_cache_write": "0.000000375", "internal_reasoning": "0.00001", "discount": 0 }, "variable_pricings": [ { "type": "prompt-threshold", "threshold": 200000, "prompt": "0.0000025", "completions": "0.000015", "input_cache_read": "0.000000625", "input_cache_write": "0.00000075" } ], "pricing_json": { "gemini:prompt_tokens": 0.00000125, "gemini:reasoning_tokens": 0.00001, "gemini:cache_read_tokens": 1.25e-7, "gemini:completion_tokens": 0.00001, "gemini:text_input_tokens": 0.00000125, "gemini:audio_input_tokens": 0.00000125, "gemini:image_input_tokens": 0.00000125, "gemini:video_input_tokens": 0.00000125, "gemini:cache_read_text_tokens": 1.25e-7, "gemini:cache_read_audio_tokens": 1.25e-7, "gemini:cache_read_image_tokens": 1.25e-7, "gemini:cache_read_video_tokens": 1.25e-7, "gemini:cache_write_storage_hours": 0.0000045, "gemini:prompt_tokens_high_context": 0.0000025, "gemini:reasoning_tokens_high_context": 0.000015, "gemini:cache_read_tokens_high_context": 2.5e-7, "gemini:completion_tokens_high_context": 0.000015, "gemini:cache_read_text_tokens_high_context": 2.5e-7, "gemini:cache_read_audio_tokens_high_context": 2.5e-7, "gemini:cache_read_image_tokens_high_context": 2.5e-7, "gemini:cache_read_video_tokens_high_context": 2.5e-7, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "9da9fe0b-1701-41e2-8b01-775ec4b54ffa", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true }, "is_mandatory_reasoning": true }, "provider_region": null, "deprecation_date": null } }, { "slug": "arcee-ai/spotlight", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-05T21:45:52.249082+00:00", "hf_updated_at": null, "name": "Arcee AI: Spotlight", "short_name": "Spotlight", "author": "arcee-ai", "description": "Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests. ", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "arcee-ai/spotlight", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "a9b3fe6f-e21f-4f3c-9ea7-f70d856939d6", "name": "Together | arcee-ai/spotlight", "context_length": 131072, "model": { "slug": "arcee-ai/spotlight", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-05T21:45:52.249082+00:00", "hf_updated_at": null, "name": "Arcee AI: Spotlight", "short_name": "Spotlight", "author": "arcee-ai", "description": "Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests. ", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "arcee-ai/spotlight", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "arcee-ai/spotlight", "model_variant_permaslug": "arcee-ai/spotlight", "adapter_name": "TogetherAdapter", "provider_name": "Together", "provider_info": { "name": "Together", "displayName": "Together", "slug": "together", "baseUrl": "https://api.together.xyz/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "TogetherAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.together.ai/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256" }, "ignoredProviderModels": [ "mixedbread-ai/Mxbai-Rerank-Large-V2", "BAAI/bge-base-en-v1.5-vllm", "scb10x/scb10x-typhoon-2-1-gemma3-12b", "arcee-ai/AFM-4.5B-Preview", "deepseek-ai/DeepSeek-R1-0528-tput", "black-forest-labs/FLUX.1-kontext-dev", "google/gemma-3-27b-it", "Qwen/Qwen3-32B-FP8", "openai/whisper-large-v3", "eddie/Qwen3-32B", "eddiehou/meta-llama/Llama-3.1-405B", "yan/deepseek-ai-deepseek-v3", "moz/Llama-3.3-70B-Instruct-Turbo", "serverless-qwen-qwen3-32b-fp8", "qwen-qwen3-32b-fp8-serverless", "moz-llama-3-3-70b-instruct-turbo", "moonshotai/Kimi-K2-Instruct-tgl-testing", "VirtueAIxTogether/VirtueGuard-Text-Lite", "Virtue-AI/VirtueGuard-Text-Lite", "black-forest-labs/FLUX.1-krea-dev", "prosus/qwen-qwen3-32b-fp8-long-context", "meta-llama/Llama-4-Scout-17B-16E-Instruct-batch", "deepseek-ai/DeepSeek-R1-DE", "arize-ai/qwen-2-1.5b-instruct", "openai/gpt-oss-120b", "meta-llama/Llama-3-70b-hf", "Qwen/Qwen2.5-72B-Instruct", "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference", "meta-llama/Llama-3.2-1B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference", "meta-llama/Meta-Llama-3-8B-Instruct", "meta-llama/Llama-3.1-405B-Instruct", "cartesia/sonic", "cartesia/sonic-2", "togethercomputer/MoA-1", "Salesforce/Llama-Rank-V1", "black-forest-labs/FLUX.1-schnell", "lgai/exaone-3-5-32b-instruct", "lgai/exaone-deep-32b", "black-forest-labs/FLUX.1-dev", "marin-community/marin-8b-instruct", "togethercomputer/Refuel-Llm-V2-Small", "meta-llama/Llama-3-70b-chat-hf", "Alibaba-NLP/gte-modernbert-base", "black-forest-labs/FLUX.1-pro", "black-forest-labs/FLUX.1.1-pro", "togethercomputer/MoA-1-Turbo", "black-forest-labs/FLUX.1-dev-lora", "meta-llama/Llama-2-70b-hf", "togethercomputer/m2-bert-80M-32k-retrieval", "togethercomputer/Refuel-Llm-V2", "intfloat/multilingual-e5-large-instruct", "black-forest-labs/FLUX.1-kontext-max", "black-forest-labs/FLUX.1-schnell-Free", "black-forest-labs/FLUX.1-kontext-pro", "BAAI/bge-large-en-v1.5", "BAAI/bge-base-en-v1.5", "Qwen/Qwen3-Next-80B-A3B-Instruct", "ServiceNow-AI/Apriel-1.5-15b-Thinker", "openai/whisper-large-v3-test", "codellama/CodeLlama-34b-Instruct-hf", "meta-llama/Llama-2-13b-chat-hf", "togethercomputer/m2-bert-80M-8k-retrieval", "WhereIsAI/UAE-Large-V1", "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro", "togethercomputer/m2-bert-80M-2k-retrieval", "meta-llama/Meta-Llama-3-70B-Instruct-Lite", "Meta-Llama/Llama-Guard-7b", "Gryphe/MythoMax-L2-13b-Lite", "upstage/SOLAR-10.7B-Instruct-v1.0", "Qwen/Qwen2.5-14B-Instruct", "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free", "zai-org/GLM-4.5-Air-FP8", "kwaivgI/kling-1.6-standard", "HiDream-ai/HiDream-I1-Full", "ByteDance-Seed/Seedream-3.0", "ByteDance-Seed/Seedream-4.0", "Lykon/DreamShaper", "HiDream-ai/HiDream-I1-Dev", "Qwen/Qwen-Image", "RunDiffusion/Juggernaut-pro-flux", "google/imagen-4.0-preview", "google/imagen-4.0-ultra", "google/veo-3.0", "minimax/hailuo-02", "stabilityai/stable-diffusion-3-medium", "black-forest-labs/FLUX.1-Canny-pro", "google/imagen-4.0-fast", "minimax/video-01-director", "HiDream-ai/HiDream-I1-Fast", "Wan-AI/Wan2.2-T2V-A14B", "ByteDance/Seedance-1.0-pro", "google/veo-3.0-fast-audio", "vidu/vidu-q1", "kwaivgI/kling-2.1-master", "google/veo-3.0-audio", "Rundiffusion/Juggernaut-Lightning-Flux", "Wan-AI/Wan2.2-I2V-A14B", "google/flash-image-2.5", "google/veo-2.0", "openai/sora-2", "google/veo-3.0-fast", "ideogram/ideogram-3.0", "kwaivgI/kling-2.0-master", "kwaivgI/kling-2.1-standard", "pixverse/pixverse-v5", "stabilityai/stable-diffusion-xl-base-1.0", "openai/sora-2-pro", "ByteDance/Seedance-1.0-lite", "kwaivgI/kling-1.6-pro", "vidu/vidu-2.0", "kwaivgI/kling-2.1-pro", "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "canopylabs/orpheus-3b-0.1-ft", "hexgrad/Kokoro-82M", "eddie/gemma-2b-it", "mistralai/Voxtral-Mini-3B-2507", "arcee-ai/coder-large", "arcee-ai/virtuoso-large", "arcee-ai/maestro-reasoning", "deepcogito/cogito-v2-1-671b", "arcee_ai/arcee-spotlight", "google/gemini-3-pro-image", "mercor/cwm", "black-forest-labs/FLUX.2-flex", "keith-aditya/kimi-k2-instruct", "pangram/mistral-small-2501", "black-forest-labs/FLUX.2-pro", "black-forest-labs/FLUX.2-dev", "ServiceNow-AI/Apriel-1.6-15b-Thinker" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Together", "provider_slug": "together", "provider_model_id": "arcee_ai/arcee-spotlight", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 65537, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "top_k", "repetition_penalty", "logit_bias", "min_p" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.together.ai/terms-of-service", "privacyPolicyURL": "https://www.together.ai/privacy" }, "pricing": { "prompt": "0.00000018", "completion": "0.00000018", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000018", "openai:completion_tokens": "0.00000018" }, "pricing_version_id": "2f14e880-0538-46ad-914f-5bda86d9d5fa", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "meta-llama/llama-guard-4-12b", "hf_slug": "meta-llama/Llama-Guard-4-12B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-30T01:06:33.531556+00:00", "hf_updated_at": null, "name": "Meta: Llama Guard 4 12B", "short_name": "Llama Guard 4 12B", "author": "meta-llama", "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\n\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.", "model_version_group_id": null, "context_length": 163840, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-guard-4-12b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "850b84c3-42a7-4cec-99c0-b5582d0da66b", "name": "DeepInfra | meta-llama/llama-guard-4-12b", "context_length": 163840, "model": { "slug": "meta-llama/llama-guard-4-12b", "hf_slug": "meta-llama/Llama-Guard-4-12B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-30T01:06:33.531556+00:00", "hf_updated_at": null, "name": "Meta: Llama Guard 4 12B", "short_name": "Llama Guard 4 12B", "author": "meta-llama", "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\n\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.", "model_version_group_id": null, "context_length": 163840, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-guard-4-12b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "meta-llama/llama-guard-4-12b", "model_variant_permaslug": "meta-llama/llama-guard-4-12b", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/bf16", "provider_model_id": "meta-llama/Llama-Guard-4-12B", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.00000018", "completion": "0.00000018", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000018", "openai:completion_tokens": "0.00000018" }, "pricing_version_id": "48e5a11b-06e3-4455-a22f-3a3af4cea914", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o4-mini-high", "hf_slug": "", "updated_at": "2026-01-08T00:53:50.4178+00:00", "created_at": "2025-04-16T17:23:32.042157+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini High", "short_name": "o4 Mini High", "author": "openai", "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o4-mini-high-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "high" ] }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "high" ] }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "60020533-2fb2-4aa1-9454-181029fd52de", "name": "OpenAI | openai/o4-mini-high-2025-04-16", "context_length": 200000, "model": { "slug": "openai/o4-mini-high", "hf_slug": "", "updated_at": "2026-01-08T00:53:50.4178+00:00", "created_at": "2025-04-16T17:23:32.042157+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini High", "short_name": "o4 Mini High", "author": "openai", "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o4-mini-high-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "high" ] }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null, "is_mandatory_reasoning": true, "supports_reasoning_effort": true, "supported_reasoning_efforts": [ "high" ] }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o4-mini-high", "model_variant_permaslug": "openai/o4-mini-high-2025-04-16", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o4-mini-2025-04-16", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000011", "completion": "0.0000044", "input_cache_read": "0.000000275", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.0000011, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.0000044, "openai_responses:cached_prompt_tokens": 2.75e-7 }, "pricing_version_id": "4bc59a87-2c2a-4682-809b-e495ce4af791", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o3", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-16T17:10:57.049467+00:00", "hf_updated_at": null, "name": "OpenAI: o3", "short_name": "o3", "author": "openai", "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o3-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "42e72619-d01c-411c-a201-f991644768b7", "name": "OpenAI | openai/o3-2025-04-16", "context_length": 200000, "model": { "slug": "openai/o3", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-16T17:10:57.049467+00:00", "hf_updated_at": null, "name": "OpenAI: o3", "short_name": "o3", "author": "openai", "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o3-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o3", "model_variant_permaslug": "openai/o3-2025-04-16", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o3-2025-04-16", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000002", "completion": "0.000008", "input_cache_read": "0.0000005", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.000002, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000008, "openai_responses:cached_prompt_tokens": 5e-7 }, "pricing_version_id": "a6ec168c-ce39-40e5-82e9-5847d89c27dd", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o4-mini", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-16T16:29:02.980764+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini", "short_name": "o4 Mini", "author": "openai", "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o4-mini-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "bd121898-b27c-4e2c-bc92-278627465a54", "name": "OpenAI | openai/o4-mini-2025-04-16", "context_length": 200000, "model": { "slug": "openai/o4-mini", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-16T16:29:02.980764+00:00", "hf_updated_at": null, "name": "OpenAI: o4 Mini", "short_name": "o4 Mini", "author": "openai", "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o4-mini-2025-04-16", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o4-mini", "model_variant_permaslug": "openai/o4-mini-2025-04-16", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o4-mini-2025-04-16", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "structured_outputs", "response_format", "seed", "max_tokens", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000011", "completion": "0.0000044", "input_cache_read": "0.000000275", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.0000011, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.0000044, "openai_responses:cached_prompt_tokens": 2.75e-7 }, "pricing_version_id": "b9791ed2-0245-490a-9ba2-eb793e43b0ec", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:23:05+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1", "short_name": "GPT-4.1", "author": "openai", "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "c235abe8-11cc-42d3-95ad-72f4d198287a", "name": "OpenAI | openai/gpt-4.1-2025-04-14", "context_length": 1047576, "model": { "slug": "openai/gpt-4.1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:23:05+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1", "short_name": "GPT-4.1", "author": "openai", "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4.1", "model_variant_permaslug": "openai/gpt-4.1-2025-04-14", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4.1-2025-04-14", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice", "temperature", "top_p" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000002", "completion": "0.000008", "input_cache_read": "0.0000005", "web_search": "0.01", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai_responses:prompt_tokens": 0.000002, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.000008, "openai_responses:cached_prompt_tokens": 5e-7 }, "pricing_version_id": "ca78388e-e63c-4cea-a999-e421ab69bfe9", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4.1-mini", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:23:01+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1 Mini", "short_name": "GPT-4.1 Mini", "author": "openai", "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-mini-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "872eccb7-9c85-45fc-974a-ff7c8e2407e6", "name": "OpenAI | openai/gpt-4.1-mini-2025-04-14", "context_length": 1047576, "model": { "slug": "openai/gpt-4.1-mini", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:23:01+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1 Mini", "short_name": "GPT-4.1 Mini", "author": "openai", "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-mini-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4.1-mini", "model_variant_permaslug": "openai/gpt-4.1-mini-2025-04-14", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4.1-mini-2025-04-14", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice", "temperature", "top_p" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000004", "completion": "0.0000016", "input_cache_read": "0.0000001", "web_search": "0.01", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.03" }, { "type": "search-threshold", "threshold": "medium", "request": "0.0275" }, { "type": "search-threshold", "threshold": "low", "request": "0.025" } ], "pricing_json": { "openai_responses:prompt_tokens": 4e-7, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 0.0000016, "openai_responses:cached_prompt_tokens": 1e-7 }, "pricing_version_id": "2ec08c1d-41c8-4a5c-a05a-14ff60a6fdd5", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4.1-nano", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:22:49+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1 Nano", "short_name": "GPT-4.1 Nano", "author": "openai", "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-nano-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "9251cee5-5503-4be9-9439-7ae21ff062a3", "name": "OpenAI | openai/gpt-4.1-nano-2025-04-14", "context_length": 1047576, "model": { "slug": "openai/gpt-4.1-nano", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-14T17:22:49+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.1 Nano", "short_name": "GPT-4.1 Nano", "author": "openai", "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.", "model_version_group_id": null, "context_length": 1047576, "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.1-nano-2025-04-14", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4.1-nano", "model_variant_permaslug": "openai/gpt-4.1-nano-2025-04-14", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4.1-nano-2025-04-14", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice", "temperature", "top_p" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000001", "completion": "0.0000004", "input_cache_read": "0.000000025", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 1e-7, "openai_responses:web_search_calls": 0.01, "openai_responses:completion_tokens": 4e-7, "openai_responses:cached_prompt_tokens": 2.5e-8 }, "pricing_version_id": "e9e74600-ce43-43ee-8cfc-ee5f7a13c045", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_native_web_search": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "meta-llama/llama-4-maverick", "hf_slug": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-05T19:37:02.129674+00:00", "hf_updated_at": null, "name": "Meta: Llama 4 Maverick", "short_name": "Llama 4 Maverick", "author": "meta-llama", "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-4-maverick-17b-128e-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "69a5d06e-1935-4aa5-903f-71058e64399f", "name": "DeepInfra | meta-llama/llama-4-maverick-17b-128e-instruct", "context_length": 1048576, "model": { "slug": "meta-llama/llama-4-maverick", "hf_slug": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-05T19:37:02.129674+00:00", "hf_updated_at": null, "name": "Meta: Llama 4 Maverick", "short_name": "Llama 4 Maverick", "author": "meta-llama", "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-4-maverick-17b-128e-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "meta-llama/llama-4-maverick", "model_variant_permaslug": "meta-llama/llama-4-maverick-17b-128e-instruct", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra/base", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/base", "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": 3342, "supported_parameters": [ "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.00000015", "completion": "0.0000006", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000015", "openai:completion_tokens": "0.0000006" }, "pricing_version_id": "8e632947-d4e4-4b41-9854-9d81e10a9e02", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "meta-llama/llama-4-scout", "hf_slug": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-05T19:31:59.735804+00:00", "hf_updated_at": null, "name": "Meta: Llama 4 Scout", "short_name": "Llama 4 Scout", "author": "meta-llama", "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\n\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.", "model_version_group_id": null, "context_length": 327680, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-4-scout-17b-16e-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "9cf05ded-eefe-41b4-8c08-0c6460feffea", "name": "DeepInfra | meta-llama/llama-4-scout-17b-16e-instruct", "context_length": 327680, "model": { "slug": "meta-llama/llama-4-scout", "hf_slug": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-05T19:31:59.735804+00:00", "hf_updated_at": null, "name": "Meta: Llama 4 Scout", "short_name": "Llama 4 Scout", "author": "meta-llama", "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\n\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.", "model_version_group_id": null, "context_length": 10000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama4", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-4-scout-17b-16e-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "meta-llama/llama-4-scout", "model_variant_permaslug": "meta-llama/llama-4-scout-17b-16e-instruct", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/fp8", "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": 3342, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.00000008", "completion": "0.0000003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000008", "openai:completion_tokens": "0.0000003" }, "pricing_version_id": "f1a26530-5938-49e1-aff6-64820dd4754c", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": false, "type_function": false }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen2.5-vl-32b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-32B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-24T18:10:38.542849+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5 VL 32B Instruct", "short_name": "Qwen2.5 VL 32B Instruct", "author": "qwen", "description": "Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It excels at visual analysis tasks, including object recognition, textual interpretation within images, and precise event localization in extended videos. Qwen2.5-VL-32B demonstrates state-of-the-art performance across multimodal benchmarks such as MMMU, MathVista, and VideoMME, while maintaining strong reasoning and clarity in text-based tasks like MMLU, mathematical problem-solving, and code generation.", "model_version_group_id": null, "context_length": 16384, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen2.5-vl-32b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "da25176f-4fdf-4f1c-8cbd-11aa2d943ec3", "name": "Chutes | qwen/qwen2.5-vl-32b-instruct", "context_length": 16384, "model": { "slug": "qwen/qwen2.5-vl-32b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-32B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-24T18:10:38.542849+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5 VL 32B Instruct", "short_name": "Qwen2.5 VL 32B Instruct", "author": "qwen", "description": "Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It excels at visual analysis tasks, including object recognition, textual interpretation within images, and precise event localization in extended videos. Qwen2.5-VL-32B demonstrates state-of-the-art performance across multimodal benchmarks such as MMMU, MathVista, and VideoMME, while maintaining strong reasoning and clarity in text-based tasks like MMLU, mathematical problem-solving, and code generation.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen2.5-vl-32b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen2.5-vl-32b-instruct", "model_variant_permaslug": "qwen/qwen2.5-vl-32b-instruct", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000005", "completion": "0.00000022", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000005", "openai:completion_tokens": "0.00000022" }, "pricing_version_id": "f15cc17b-4cc0-4f96-a76b-e1664fb8ed62", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o1-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-19T22:26:51.610039+00:00", "hf_updated_at": null, "name": "OpenAI: o1-pro", "short_name": "o1-pro", "author": "openai", "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o1-pro", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "046ae30d-fe99-44b4-b020-21127e4342c7", "name": "OpenAI | openai/o1-pro", "context_length": 200000, "model": { "slug": "openai/o1-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-19T22:26:51.610039+00:00", "hf_updated_at": null, "name": "OpenAI: o1-pro", "short_name": "o1-pro", "author": "openai", "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o1-pro", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o1-pro", "model_variant_permaslug": "openai/o1-pro", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o1-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "seed", "max_tokens", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00015", "completion": "0.0006", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.00015, "openai_responses:completion_tokens": 0.0006 }, "pricing_version_id": "af47ffe6-72c7-4a72-8bf4-1922ed5d6d65", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-small-3.1-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-17T19:15:37.00423+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.1 24B (free)", "short_name": "Mistral Small 3.1 24B (free)", "author": "mistralai", "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "ecbdc9f1-ecca-4f91-83cf-b3495a60e874", "name": "Venice | mistralai/mistral-small-3.1-24b-instruct-2503:free", "context_length": 128000, "model": { "slug": "mistralai/mistral-small-3.1-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-17T19:15:37.00423+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.1 24B", "short_name": "Mistral Small 3.1 24B", "author": "mistralai", "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-small-3.1-24b-instruct:free", "model_variant_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503:free", "adapter_name": "VeniceAdapter", "provider_name": "Venice", "provider_info": { "name": "Venice", "displayName": "Venice", "slug": "venice", "baseUrl": "https://api.venice.ai/api/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://venice.ai/legal/tos", "privacyPolicyURL": "https://venice.ai/legal/privacy-policy" }, "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "VeniceAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://venice.ai/&size=256" }, "ignoredProviderModels": [ "llama-3.2-3b", "deepseek-coder-v2-lite", "dolphin-2.9.2-qwen2-72b", "mistral-32-24b", "zai-org-glm-4.6", "qwen3-235b-a22b-thinking-2507", "qwen3-235b-a22b-instruct-2507", "google-gemma-3-27b-it", "openai-gpt-oss-120b", "deepseek-ai-DeepSeek-R1", "grok-41-fast", "gemini-3-pro-preview", "claude-opus-45", "kimi-k2-thinking", "deepseek-v3.2", "openai-gpt-52", "gemini-3-flash-preview", "grok-code-fast-1", "claude-sonnet-45", "openai-gpt-52-codex", "venice-uncensored", "qwen3-4b", "mistral-31-24b", "qwen3-next-80b", "qwen3-coder-480b-a35b-instruct", "hermes-3-llama-3.1-405b", "llama-3.3-70b" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Venice", "provider_slug": "venice/fp8", "provider_model_id": "mistral-31-24b", "quantization": "fp8", "variant": "free", "is_free": true, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "structured_outputs", "response_format", "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "top_k", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://venice.ai/legal/tos", "privacyPolicyURL": "https://venice.ai/legal/privacy-policy" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0", "openai:completion_tokens": "0" }, "pricing_version_id": "ea23abca-d690-46fc-bfe7-f9b7131fec90", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": 8, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "disable_free_endpoint_limits": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "response_format": true, "structured_outputs": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/mistral-small-3.1-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-17T19:15:37.00423+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.1 24B", "short_name": "Mistral Small 3.1 24B", "author": "mistralai", "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "5f981bd9-b098-4757-b075-06d51d37cc65", "name": "Chutes | mistralai/mistral-small-3.1-24b-instruct-2503", "context_length": 131072, "model": { "slug": "mistralai/mistral-small-3.1-24b-instruct", "hf_slug": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-17T19:15:37.00423+00:00", "hf_updated_at": null, "name": "Mistral: Mistral Small 3.1 24B", "short_name": "Mistral Small 3.1 24B", "author": "mistralai", "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/mistral-small-3.1-24b-instruct", "model_variant_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "chutesai/Mistral-Small-3.1-24B-Instruct-2503", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 131072, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "tools", "tool_choice", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000003", "completion": "0.00000011", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000003", "openai:completion_tokens": "0.00000011" }, "pricing_version_id": "8f9bd506-357e-41cb-b7e8-f8f5b7b4d123", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-4b-it", "hf_slug": "google/gemma-3-4b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T22:38:30.653142+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 4B (free)", "short_name": "Gemma 3 4B (free)", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-4b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "90fbd988-266d-4ef4-b345-63b46ab6caca", "name": "Google AI Studio | google/gemma-3-4b-it:free", "context_length": 32768, "model": { "slug": "google/gemma-3-4b-it", "hf_slug": "google/gemma-3-4b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T22:38:30.653142+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 4B", "short_name": "Gemma 3 4B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-4b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-4b-it:free", "model_variant_permaslug": "google/gemma-3-4b-it:free", "adapter_name": "GoogleAIStudioGeminiAdapter", "provider_name": "Google AI Studio", "provider_info": { "name": "Google AI Studio", "displayName": "Google AI Studio", "slug": "google-ai-studio", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleAIStudioGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "/images/icons/GoogleAIStudio.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-1p", "gemini-2.5-pro-1p-recitation-off", "gemini-2.5-flash-1p", "gemini-2.5-flash-1p-recitation-off", "gemini-2.5-flash-lite-preview-06-11-summarized", "gemini-2.5-flash", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-1.5-pro-latest", "gemini-1.5-pro", "gemini-1.5-flash-latest", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-1.5-flash-8b-latest", "gemini-2.5-pro-preview-03-25", "gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-preview", "gemini-2.0-pro-exp", "gemini-2.0-flash-thinking-exp", "gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts", "learnlm-2.0-flash-experimental", "gracefulgolem", "gemini-2.5-flash-preview-05-20", "gemini-2.5-pro-preview-06-05", "gemini-2.0-flash-exp-image-generation", "gemini-2.0-flash-preview-image-generation", "gemini-2.0-flash-lite-preview-02-05", "gemini-2.0-pro-exp-02-05", "gemini-exp-1206", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-flash-thinking-exp-1219", "gemma-3-1b-it", "gemini-flash-latest", "gemini-flash-lite-latest", "gemini-pro-latest", "gemini-robotics-er-1.5-preview", "gemini-embedding-001", "riftrunner-fst-rewind", "gemini-3-pro-image-preview", "nano-banana-pro-preview", "fiercefalcon", "fiercefalcon-inline-citation", "fiercefalcon-blocked-sites" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google AI Studio", "provider_slug": "google-ai-studio", "provider_model_id": "gemma-3-4b-it", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "response_format", "stop" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 0, "gemini:reasoning_tokens": 0, "gemini:completion_tokens": 0, "gemini:text_input_tokens": 0, "gemini:audio_input_tokens": 0, "gemini:image_input_tokens": 0, "gemini:video_input_tokens": 0, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "5910cac3-cd98-4e8a-8aa1-95d0ecfd5f88", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "structured_outputs": false } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-4b-it", "hf_slug": "google/gemma-3-4b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T22:38:30.653142+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 4B", "short_name": "Gemma 3 4B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 96000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-4b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "82b95f58-a96f-4ace-bbfa-8ab8443c9d15", "name": "Chutes | google/gemma-3-4b-it", "context_length": 96000, "model": { "slug": "google/gemma-3-4b-it", "hf_slug": "google/gemma-3-4b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T22:38:30.653142+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 4B", "short_name": "Gemma 3 4B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-4b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-4b-it", "model_variant_permaslug": "google/gemma-3-4b-it", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes", "provider_model_id": "unsloth/gemma-3-4b-it", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000001703012", "completion": "0.0000000681536", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000001703012", "openai:completion_tokens": "0.0000000681536" }, "pricing_version_id": "f1fa869b-f892-461c-858e-c77dc890f169", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-12b-it", "hf_slug": "google/gemma-3-12b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T21:50:25.140801+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 12B (free)", "short_name": "Gemma 3 12B (free)", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-12b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "a6489e9a-e430-438f-9aa9-d6a664362e6e", "name": "Google AI Studio | google/gemma-3-12b-it:free", "context_length": 32768, "model": { "slug": "google/gemma-3-12b-it", "hf_slug": "google/gemma-3-12b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T21:50:25.140801+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 12B", "short_name": "Gemma 3 12B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-12b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-12b-it:free", "model_variant_permaslug": "google/gemma-3-12b-it:free", "adapter_name": "GoogleAIStudioGeminiAdapter", "provider_name": "Google AI Studio", "provider_info": { "name": "Google AI Studio", "displayName": "Google AI Studio", "slug": "google-ai-studio", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleAIStudioGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "/images/icons/GoogleAIStudio.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-1p", "gemini-2.5-pro-1p-recitation-off", "gemini-2.5-flash-1p", "gemini-2.5-flash-1p-recitation-off", "gemini-2.5-flash-lite-preview-06-11-summarized", "gemini-2.5-flash", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-1.5-pro-latest", "gemini-1.5-pro", "gemini-1.5-flash-latest", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-1.5-flash-8b-latest", "gemini-2.5-pro-preview-03-25", "gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-preview", "gemini-2.0-pro-exp", "gemini-2.0-flash-thinking-exp", "gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts", "learnlm-2.0-flash-experimental", "gracefulgolem", "gemini-2.5-flash-preview-05-20", "gemini-2.5-pro-preview-06-05", "gemini-2.0-flash-exp-image-generation", "gemini-2.0-flash-preview-image-generation", "gemini-2.0-flash-lite-preview-02-05", "gemini-2.0-pro-exp-02-05", "gemini-exp-1206", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-flash-thinking-exp-1219", "gemma-3-1b-it", "gemini-flash-latest", "gemini-flash-lite-latest", "gemini-pro-latest", "gemini-robotics-er-1.5-preview", "gemini-embedding-001", "riftrunner-fst-rewind", "gemini-3-pro-image-preview", "nano-banana-pro-preview", "fiercefalcon", "fiercefalcon-inline-citation", "fiercefalcon-blocked-sites" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google AI Studio", "provider_slug": "google-ai-studio", "provider_model_id": "gemma-3-12b-it", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "stop" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 0, "gemini:reasoning_tokens": 0, "gemini:completion_tokens": 0, "gemini:text_input_tokens": 0, "gemini:audio_input_tokens": 0, "gemini:image_input_tokens": 0, "gemini:video_input_tokens": 0, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "0140f5a5-97fd-4ac9-ac62-e7132fb22336", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": { "structured_outputs": false } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-12b-it", "hf_slug": "google/gemma-3-12b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T21:50:25.140801+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 12B", "short_name": "Gemma 3 12B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-12b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "3d994016-72a0-497c-a16a-22eff393ab2a", "name": "Chutes | google/gemma-3-12b-it", "context_length": 131072, "model": { "slug": "google/gemma-3-12b-it", "hf_slug": "google/gemma-3-12b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-13T21:50:25.140801+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 12B", "short_name": "Gemma 3 12B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-12b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-12b-it", "model_variant_permaslug": "google/gemma-3-12b-it", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "unsloth/gemma-3-12b-it", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 131072, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000003", "completion": "0.0000001", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000003", "openai:completion_tokens": "0.0000001" }, "pricing_version_id": "410a115b-b30c-4039-9667-726659fdd9ff", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-27b-it", "hf_slug": "google/gemma-3-27b-it", "updated_at": "2026-01-07T04:36:03.22387+00:00", "created_at": "2025-03-12T05:12:39.645813+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 27B (free)", "short_name": "Gemma 3 27B (free)", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-27b-it", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "f4276f71-4f8b-48e5-a823-42260e7c0965", "name": "ModelRun | google/gemma-3-27b-it:free", "context_length": 131072, "model": { "slug": "google/gemma-3-27b-it", "hf_slug": "google/gemma-3-27b-it", "updated_at": "2026-01-07T04:36:03.22387+00:00", "created_at": "2025-03-12T05:12:39.645813+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 27B", "short_name": "Gemma 3 27B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-27b-it", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-27b-it:free", "model_variant_permaslug": "google/gemma-3-27b-it:free", "adapter_name": "OpenAIAdapter", "provider_name": "ModelRun", "provider_info": { "name": "ModelRun", "displayName": "ModelRun", "slug": "modelrun", "baseUrl": "https://api.runmodelrun.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.runmodelrun.com/TOS.html", "privacyPolicyURL": "https://www.runmodelrun.com/privacy-policy.html" }, "headquarters": "US", "datacenters": [ "US" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://api.runmodelrun.com&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "ModelRun", "provider_slug": "modelrun", "provider_model_id": "google/gemma-3-27b-it", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "presence_penalty", "repetition_penalty", "frequency_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.runmodelrun.com/TOS.html", "privacyPolicyURL": "https://www.runmodelrun.com/privacy-policy.html" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": 0, "openai:completion_tokens": 0 }, "pricing_version_id": "d2453ad7-a13c-4d55-99d7-bdc5162c7d4e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": false, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_multipart": false, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemma-3-27b-it", "hf_slug": "google/gemma-3-27b-it", "updated_at": "2026-01-07T04:36:03.22387+00:00", "created_at": "2025-03-12T05:12:39.645813+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 27B", "short_name": "Gemma 3 27B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 96000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-27b-it", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "0618de82-14d9-41e5-98f9-51bccf805320", "name": "Chutes | google/gemma-3-27b-it", "context_length": 96000, "model": { "slug": "google/gemma-3-27b-it", "hf_slug": "google/gemma-3-27b-it", "updated_at": "2026-01-07T04:36:03.22387+00:00", "created_at": "2025-03-12T05:12:39.645813+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 27B", "short_name": "Gemma 3 27B", "author": "google", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-27b-it", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemma-3-27b-it", "model_variant_permaslug": "google/gemma-3-27b-it", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "unsloth/gemma-3-27b-it", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 96000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "tools", "tool_choice", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000004", "completion": "0.00000015", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000004", "openai:completion_tokens": "0.00000015" }, "pricing_version_id": "280251e1-c249-418e-85fd-31963ef6b92a", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "perplexity/sonar-reasoning-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-07T02:08:28.125446+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Reasoning Pro", "short_name": "Sonar Reasoning Pro", "author": "perplexity", "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nSonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": "deepseek-r1", "default_system": null, "default_stops": [ "<｜User｜>", "<｜end▁of▁sentence｜>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar-reasoning-pro", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "" }, "features": { "reasoning_config": { "start_token": "", "end_token": "" } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "0d28660e-435a-4853-a2c6-9d916df28fc7", "name": "Perplexity | perplexity/sonar-reasoning-pro", "context_length": 128000, "model": { "slug": "perplexity/sonar-reasoning-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-07T02:08:28.125446+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Reasoning Pro", "short_name": "Sonar Reasoning Pro", "author": "perplexity", "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nSonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": "deepseek-r1", "default_system": null, "default_stops": [ "<｜User｜>", "<｜end▁of▁sentence｜>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar-reasoning-pro", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "" }, "features": { "reasoning_config": { "start_token": "", "end_token": "" } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "perplexity/sonar-reasoning-pro", "model_variant_permaslug": "perplexity/sonar-reasoning-pro", "adapter_name": "PerplexityAdapter", "provider_name": "Perplexity", "provider_info": { "name": "Perplexity", "displayName": "Perplexity", "slug": "perplexity", "baseUrl": "https://api.perplexity.ai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "PerplexityAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.perplexity.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Perplexity.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Perplexity", "provider_slug": "perplexity", "provider_model_id": "sonar-reasoning-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "reasoning", "include_reasoning", "max_tokens", "temperature", "top_p", "top_k", "frequency_penalty", "presence_penalty", "web_search_options" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "pricing": { "prompt": "0.000002", "completion": "0.000008", "image": "0", "request": "0", "web_search": "0.005", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.014" }, { "type": "search-threshold", "threshold": "medium", "request": "0.01" }, { "type": "search-threshold", "threshold": "low", "request": "0.006" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "perplexity/sonar-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-07T01:53:43+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Pro", "short_name": "Sonar Pro", "author": "perplexity", "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nFor enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions. ", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar-pro", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "e19b1036-fab9-4f97-9579-8ea67959cc9b", "name": "Perplexity | perplexity/sonar-pro", "context_length": 200000, "model": { "slug": "perplexity/sonar-pro", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-07T01:53:43+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar Pro", "short_name": "Sonar Pro", "author": "perplexity", "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nFor enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions. ", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar-pro", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "perplexity/sonar-pro", "model_variant_permaslug": "perplexity/sonar-pro", "adapter_name": "PerplexityAdapter", "provider_name": "Perplexity", "provider_info": { "name": "Perplexity", "displayName": "Perplexity", "slug": "perplexity", "baseUrl": "https://api.perplexity.ai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "PerplexityAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.perplexity.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Perplexity.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Perplexity", "provider_slug": "perplexity", "provider_model_id": "sonar-pro", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "frequency_penalty", "presence_penalty", "web_search_options" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "image": "0", "request": "0", "web_search": "0.005", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.014" }, { "type": "search-threshold", "threshold": "medium", "request": "0.01" }, { "type": "search-threshold", "threshold": "low", "request": "0.006" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_multipart": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.0-flash-lite-001", "hf_slug": "", "updated_at": "2025-11-14T23:32:47.563595+00:00", "created_at": "2025-02-25T17:56:52.206054+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash Lite", "short_name": "Gemini 2.0 Flash Lite", "author": "google", "description": "Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5), all at extremely economical token prices.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-lite-001", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "4dc03b46-4015-495b-acff-1dcacb6c3311", "name": "Google | google/gemini-2.0-flash-lite-001", "context_length": 1048576, "model": { "slug": "google/gemini-2.0-flash-lite-001", "hf_slug": "", "updated_at": "2025-11-14T23:32:47.563595+00:00", "created_at": "2025-02-25T17:56:52.206054+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash Lite", "short_name": "Gemini 2.0 Flash Lite", "author": "google", "description": "Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5), all at extremely economical token prices.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-lite-001", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.0-flash-lite-001", "model_variant_permaslug": "google/gemini-2.0-flash-lite-001", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.0-flash-lite-001", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "response_format", "stop", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000000075", "completion": "0.0000003", "image": "0.000000075", "audio": "0.000000075", "internal_reasoning": "0.0000003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 7.5e-8, "gemini:reasoning_tokens": 3e-7, "gemini:completion_tokens": 3e-7, "gemini:text_input_tokens": 7.5e-8, "gemini:audio_input_tokens": 7.5e-8, "gemini:image_input_tokens": 7.5e-8, "gemini:video_input_tokens": 7.5e-8, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "34326346-6ef6-4ae4-812f-8efa6243856d", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {}, "supports_input_audio": true }, "provider_region": null, "deprecation_date": "2026-03-03" } }, { "slug": "anthropic/claude-3.7-sonnet", "hf_slug": "", "updated_at": "2025-12-05T21:54:07.586262+00:00", "created_at": "2025-02-24T18:35:10.00008+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.7 Sonnet (thinking)", "short_name": "Claude 3.7 Sonnet (thinking)", "author": "anthropic", "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-7-sonnet-20250219", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "aa1ee54a-c660-496a-8f2d-d8470ef3f11b", "name": "Google | anthropic/claude-3-7-sonnet-20250219:thinking", "context_length": 200000, "model": { "slug": "anthropic/claude-3.7-sonnet", "hf_slug": "", "updated_at": "2025-12-05T21:54:07.586262+00:00", "created_at": "2025-02-24T18:35:10.00008+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.7 Sonnet", "short_name": "Claude 3.7 Sonnet", "author": "anthropic", "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-7-sonnet-20250219", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-3.7-sonnet:thinking", "model_variant_permaslug": "anthropic/claude-3-7-sonnet-20250219:thinking", "adapter_name": "GoogleVertexAnthropicAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "claude-3-7-sonnet@20250219", "quantization": "unknown", "variant": "thinking", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "top_p", "temperature", "stop", "reasoning", "include_reasoning", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "input_cache_read": "0.0000003", "input_cache_write": "0.00000375", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000003, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 3e-7, "anthropic:completion_tokens": 0.000015, "anthropic:cache_write_1h_tokens": 0.000006, "anthropic:cache_write_5m_tokens": 0.00000375 }, "pricing_version_id": "42f7eb91-30f9-4d8e-bd2e-a584e9b6edaa", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-3.7-sonnet", "hf_slug": "", "updated_at": "2025-12-05T21:54:07.586262+00:00", "created_at": "2025-02-24T18:35:10.00008+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.7 Sonnet", "short_name": "Claude 3.7 Sonnet", "author": "anthropic", "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-7-sonnet-20250219", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "1c9b8776-e266-4efb-b5ba-19a6753e7736", "name": "Google | anthropic/claude-3-7-sonnet-20250219", "context_length": 200000, "model": { "slug": "anthropic/claude-3.7-sonnet", "hf_slug": "", "updated_at": "2025-12-05T21:54:07.586262+00:00", "created_at": "2025-02-24T18:35:10.00008+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.7 Sonnet", "short_name": "Claude 3.7 Sonnet", "author": "anthropic", "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-7-sonnet-20250219", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "amazon-bedrock", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-3.7-sonnet", "model_variant_permaslug": "anthropic/claude-3-7-sonnet-20250219", "adapter_name": "GoogleVertexAnthropicAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex/us", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex/us", "provider_model_id": "claude-3-7-sonnet@20250219", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "top_p", "temperature", "stop", "reasoning", "include_reasoning", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0.000003", "completion": "0.000015", "input_cache_read": "0.0000003", "input_cache_write": "0.00000375", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000003, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 3e-7, "anthropic:completion_tokens": 0.000015, "anthropic:cache_write_1h_tokens": 0.000006, "anthropic:cache_write_5m_tokens": 0.00000375 }, "pricing_version_id": "0c3c8e44-3744-4eb9-b1ef-59291e23b8fd", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": true, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.0-flash-001", "hf_slug": "", "updated_at": "2025-11-14T23:34:05.685679+00:00", "created_at": "2025-02-05T15:30:13.144552+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash", "short_name": "Gemini 2.0 Flash", "author": "google", "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1048576, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-001", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "8b6c3ec6-e6a0-43f7-9e09-a5487a5756c9", "name": "Google AI Studio | google/gemini-2.0-flash-001", "context_length": 1048576, "model": { "slug": "google/gemini-2.0-flash-001", "hf_slug": "", "updated_at": "2025-11-14T23:34:05.685679+00:00", "created_at": "2025-02-05T15:30:13.144552+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash", "short_name": "Gemini 2.0 Flash", "author": "google", "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1000000, "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-001", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.0-flash-001", "model_variant_permaslug": "google/gemini-2.0-flash-001", "adapter_name": "GoogleAIStudioGeminiAdapter", "provider_name": "Google AI Studio", "provider_info": { "name": "Google AI Studio", "displayName": "Google AI Studio", "slug": "google-ai-studio", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleAIStudioGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "/images/icons/GoogleAIStudio.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-1p", "gemini-2.5-pro-1p-recitation-off", "gemini-2.5-flash-1p", "gemini-2.5-flash-1p-recitation-off", "gemini-2.5-flash-lite-preview-06-11-summarized", "gemini-2.5-flash", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-1.5-pro-latest", "gemini-1.5-pro", "gemini-1.5-flash-latest", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-1.5-flash-8b-latest", "gemini-2.5-pro-preview-03-25", "gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-preview", "gemini-2.0-pro-exp", "gemini-2.0-flash-thinking-exp", "gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts", "learnlm-2.0-flash-experimental", "gracefulgolem", "gemini-2.5-flash-preview-05-20", "gemini-2.5-pro-preview-06-05", "gemini-2.0-flash-exp-image-generation", "gemini-2.0-flash-preview-image-generation", "gemini-2.0-flash-lite-preview-02-05", "gemini-2.0-pro-exp-02-05", "gemini-exp-1206", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-flash-thinking-exp-1219", "gemma-3-1b-it", "gemini-flash-latest", "gemini-flash-lite-latest", "gemini-pro-latest", "gemini-robotics-er-1.5-preview", "gemini-embedding-001", "riftrunner-fst-rewind", "gemini-3-pro-image-preview", "nano-banana-pro-preview", "fiercefalcon", "fiercefalcon-inline-citation", "fiercefalcon-blocked-sites" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google AI Studio", "provider_slug": "google-ai-studio", "provider_model_id": "gemini-2.0-flash-001", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "response_format", "stop", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice" }, "pricing": { "prompt": "0.0000001", "completion": "0.0000004", "image": "0.0000001", "audio": "0.0000007", "input_audio_cache": "0.000000175", "input_cache_read": "0.000000025", "input_cache_write": "0.00000008333333333333334", "internal_reasoning": "0.0000004", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": 1e-7, "gemini:reasoning_tokens": 4e-7, "gemini:cache_read_tokens": 2.5e-8, "gemini:completion_tokens": 4e-7, "gemini:text_input_tokens": 1e-7, "gemini:audio_input_tokens": 7e-7, "gemini:image_input_tokens": 1e-7, "gemini:video_input_tokens": 1e-7, "gemini:cache_read_text_tokens": 2.5e-8, "gemini:cache_read_audio_tokens": 1.75e-7, "gemini:cache_read_image_tokens": 2.5e-8, "gemini:cache_read_video_tokens": 2.5e-8, "gemini:cache_write_storage_hours": 0.000001, "gemini:cache_read_tokens_high_context": 5e-8, "gemini:cache_read_text_tokens_high_context": 5e-8, "gemini:cache_read_audio_tokens_high_context": 3.5e-7, "gemini:cache_read_image_tokens_high_context": 5e-8, "gemini:cache_read_video_tokens_high_context": 5e-8, "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "f232c68f-eb0d-4d69-948e-a854a9b49d01", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_base64_video_input": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": true }, "provider_region": null, "deprecation_date": "2026-03-31" } }, { "slug": "qwen/qwen-vl-plus", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-05T04:54:15.216448+00:00", "hf_updated_at": null, "name": "Qwen: Qwen VL Plus", "short_name": "Qwen VL Plus", "author": "qwen", "description": "Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for image input. It delivers significant performance across a broad range of visual tasks.\n", "model_version_group_id": null, "context_length": 7500, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-vl-plus", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "df9c15ac-870b-40e5-aa43-e4b3b44951f7", "name": "Alibaba | qwen/qwen-vl-plus", "context_length": 7500, "model": { "slug": "qwen/qwen-vl-plus", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-05T04:54:15.216448+00:00", "hf_updated_at": null, "name": "Qwen: Qwen VL Plus", "short_name": "Qwen VL Plus", "author": "qwen", "description": "Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for image input. It delivers significant performance across a broad range of visual tasks.\n", "model_version_group_id": null, "context_length": 7500, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-vl-plus", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen-vl-plus", "model_variant_permaslug": "qwen/qwen-vl-plus", "adapter_name": "AlibabaAdapter", "provider_name": "Alibaba", "provider_info": { "name": "Alibaba", "displayName": "Alibaba Cloud Int.", "slug": "alibaba", "baseUrl": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "headquarters": "SG", "datacenters": [ "SG", "CN" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AlibabaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.alibabacloud.com/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Alibaba Cloud Int.", "provider_slug": "alibaba", "provider_model_id": "qwen-vl-plus", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": 6000, "max_completion_tokens": 1500, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "presence_penalty", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "pricing": { "prompt": "0.00000021", "completion": "0.00000063", "image": "0.0002688", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen-vl-max", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-01T18:25:04.223655+00:00", "hf_updated_at": null, "name": "Qwen: Qwen VL Max", "short_name": "Qwen VL Max", "author": "qwen", "description": "Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.\n", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-vl-max-2025-01-25", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "40a33c72-3801-49f3-ac2a-966d0b249981", "name": "Alibaba | qwen/qwen-vl-max-2025-01-25", "context_length": 131072, "model": { "slug": "qwen/qwen-vl-max", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-01T18:25:04.223655+00:00", "hf_updated_at": null, "name": "Qwen: Qwen VL Max", "short_name": "Qwen VL Max", "author": "qwen", "description": "Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.\n", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-vl-max-2025-01-25", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen-vl-max", "model_variant_permaslug": "qwen/qwen-vl-max-2025-01-25", "adapter_name": "AlibabaAdapter", "provider_name": "Alibaba", "provider_info": { "name": "Alibaba", "displayName": "Alibaba Cloud Int.", "slug": "alibaba", "baseUrl": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "headquarters": "SG", "datacenters": [ "SG", "CN" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AlibabaAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.alibabacloud.com/", "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Alibaba Cloud Int.", "provider_slug": "alibaba", "provider_model_id": "qwen-vl-max-2025-08-13", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": 129024, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "presence_penalty", "response_format", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacyPolicyURL": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy" }, "pricing": { "prompt": "0.0000008", "completion": "0.0000032", "image": "0.001024", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen2.5-vl-72b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-72B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-01T11:45:11.997326+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5 VL 72B Instruct", "short_name": "Qwen2.5 VL 72B Instruct", "author": "qwen", "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen2.5-vl-72b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "f80f9c7d-2b54-4ee2-bb8f-c8a46fde38d2", "name": "Chutes | qwen/qwen2.5-vl-72b-instruct", "context_length": 32768, "model": { "slug": "qwen/qwen2.5-vl-72b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-72B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-01T11:45:11.997326+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5 VL 72B Instruct", "short_name": "Qwen2.5 VL 72B Instruct", "author": "qwen", "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen2.5-vl-72b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen2.5-vl-72b-instruct", "model_variant_permaslug": "qwen/qwen2.5-vl-72b-instruct", "adapter_name": "ChutesAdapter", "provider_name": "Chutes", "provider_info": { "name": "Chutes", "displayName": "Chutes", "slug": "chutes", "baseUrl": "https://llm.chutes.ai/v1", "dataPolicy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "ChutesAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256" }, "ignoredProviderModels": [ "openbmb/MiniCPM4-8B", "agentica-org/DeepSWE-Preview", "moonshotai/Kimi-K2-Instruct-tools", "internlm/Intern-S1", "TheDrummer/Gemmasutra-Pro-27B-v1.1", "all-hands/openhands-lm-32b-v0.1-ep3", "TheDrummer/Tunguska-39B-v1", "Meridian", "Zenith", "Proxima", "agentica-org/DeepCoder-14B-Preview", "TheDrummer/Cydonia-24B-v2.1", "Tesslate/UIGEN-X-32B-0727", "NousResearch/Hermes-4-14B", "unsloth/gemma-3-4b-it", "tencent/Hunyuan-A13B-Instruct", "unsloth/Llama-3.2-3B-Instruct", "unsloth/Llama-3.2-1B-Instruct", "zai-org/GLM-4.5-turbo", "zai-org/GLM-4.6-turbo", "rednote-hilab/dots.ocr", "deepseek-ai/DeepSeek-V3-0324-turbo", "deepseek-ai/DeepSeek-V3.1-turbo", "moonshotai/Kimi-K2-Thinking", "zai-org/GLM-4.5", "deepseek-ai/DeepSeek-V3.1", "zai-org/GLM-4.6-FP8", "zai-org/GLM-4.7-FP8", "zai-org/GLM-4.5-FP8" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Chutes", "provider_slug": "chutes/bf16", "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct-TEE", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 32768, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "top_k", "repetition_penalty", "response_format", "structured_outputs" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://chutes.ai/tos" }, "pricing": { "prompt": "0.00000015", "completion": "0.0000006", "image": "0", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.00000015", "openai:completion_tokens": "0.0000006" }, "pricing_version_id": "ef3a118d-6cc7-498d-a4df-3c3f82eb2f6e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "perplexity/sonar", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-01-27T21:36:48.666939+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar", "short_name": "Sonar", "author": "perplexity", "description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.", "model_version_group_id": null, "context_length": 127072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "5f831e7a-c555-4d3a-b228-88286347558a", "name": "Perplexity | perplexity/sonar", "context_length": 127072, "model": { "slug": "perplexity/sonar", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-01-27T21:36:48.666939+00:00", "hf_updated_at": null, "name": "Perplexity: Sonar", "short_name": "Sonar", "author": "perplexity", "description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.", "model_version_group_id": null, "context_length": 127072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "perplexity/sonar", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "perplexity/sonar", "model_variant_permaslug": "perplexity/sonar", "adapter_name": "PerplexityAdapter", "provider_name": "Perplexity", "provider_info": { "name": "Perplexity", "displayName": "Perplexity", "slug": "perplexity", "baseUrl": "https://api.perplexity.ai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "PerplexityAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.perplexity.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Perplexity.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Perplexity", "provider_slug": "perplexity", "provider_model_id": "sonar", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "frequency_penalty", "presence_penalty", "web_search_options" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacyPolicyURL": "https://www.perplexity.ai/hub/legal/privacy-policy" }, "pricing": { "prompt": "0.000001", "completion": "0.000001", "image": "0", "request": "0.005", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.012" }, { "type": "search-threshold", "threshold": "medium", "request": "0.008" }, { "type": "search-threshold", "threshold": "low", "request": "0.005" } ], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "minimax/minimax-01", "hf_slug": "MiniMaxAI/MiniMax-Text-01", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-01-15T04:31:02.677929+00:00", "hf_updated_at": null, "name": "MiniMax: MiniMax-01", "short_name": "MiniMax-01", "author": "minimax", "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens.\n\nThe text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.\n\nTo read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2", "model_version_group_id": null, "context_length": 1000192, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "minimax/minimax-01", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "352546d2-3758-4aa1-9e98-e1a83748aa4e", "name": "Minimax | minimax/minimax-01", "context_length": 1000192, "model": { "slug": "minimax/minimax-01", "hf_slug": "MiniMaxAI/MiniMax-Text-01", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-01-15T04:31:02.677929+00:00", "hf_updated_at": null, "name": "MiniMax: MiniMax-01", "short_name": "MiniMax-01", "author": "minimax", "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens.\n\nThe text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.\n\nTo read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "minimax/minimax-01", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "minimax/minimax-01", "model_variant_permaslug": "minimax/minimax-01", "adapter_name": "MinimaxAdapter", "provider_name": "Minimax", "provider_info": { "name": "Minimax", "displayName": "MiniMax", "slug": "minimax", "baseUrl": "https://api.minimaxi.chat/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.minimax.io/platform/protocol/terms-of-service", "privacyPolicyURL": "https://www.minimax.io/platform/protocol/privacy-policy" }, "headquarters": "SG", "datacenters": [ "US" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MinimaxAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://minimaxi.com/&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "MiniMax", "provider_slug": "minimax", "provider_model_id": "MiniMax-Text-01", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 1000192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://www.minimax.io/platform/protocol/terms-of-service", "privacyPolicyURL": "https://www.minimax.io/platform/protocol/privacy-policy" }, "pricing": { "prompt": "0.0000002", "completion": "0.0000011", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000002", "openai:completion_tokens": "0.0000011" }, "pricing_version_id": "6bea1ceb-8249-4f88-b48c-f90eb7df1ab0", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/o1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-17T18:26:39.576639+00:00", "hf_updated_at": null, "name": "OpenAI: o1", "short_name": "o1", "author": "openai", "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o1-2024-12-17", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "82738f61-f3cb-44a5-b5d1-e6787ae64e3b", "name": "OpenAI | openai/o1-2024-12-17", "context_length": 200000, "model": { "slug": "openai/o1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-17T18:26:39.576639+00:00", "hf_updated_at": null, "name": "OpenAI: o1", "short_name": "o1", "author": "openai", "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "openai/o1-2024-12-17", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/o1", "model_variant_permaslug": "openai/o1-2024-12-17", "adapter_name": "OpenAIResponsesAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIResponsesAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_responses" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "o1-2024-12-17", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 100000, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000015", "completion": "0.00006", "input_cache_read": "0.0000075", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai_responses:prompt_tokens": 0.000015, "openai_responses:completion_tokens": 0.00006, "openai_responses:cached_prompt_tokens": 0.0000075 }, "pricing_version_id": "c7fe5d08-4ae8-494a-80a6-7452307c6540", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_file_urls": true, "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "google/gemini-2.0-flash-exp", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-11T17:18:43.999311+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash Experimental (free)", "short_name": "Gemini 2.0 Flash Experimental (free)", "author": "google", "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1048576, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-exp", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "65df650a-3eae-46b0-b5b0-87546ca90cc3", "name": "Google | google/gemini-2.0-flash-exp:free", "context_length": 1048576, "model": { "slug": "google/gemini-2.0-flash-exp", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-11T17:18:43.999311+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.0 Flash Experimental", "short_name": "Gemini 2.0 Flash Experimental", "author": "google", "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.", "model_version_group_id": "e993dfbf-2cbd-4680-b866-c05bbdcc8f4d", "context_length": 1048576, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.0-flash-exp", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "google/gemini-2.0-flash-exp:free", "model_variant_permaslug": "google/gemini-2.0-flash-exp:free", "adapter_name": "GoogleVertexGeminiAdapter", "provider_name": "Google", "provider_info": { "name": "Google", "displayName": "Google Vertex", "slug": "google-vertex", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "not-used" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "GoogleVertexGeminiAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history", "byokEnabled": true, "icon": { "url": "/images/icons/GoogleVertex.svg" }, "ignoredProviderModels": [ "gemini-2.5-pro-exp-03-25", "gemini-2.0-flash-exp", "gemini-1.5-flash-002", "gemini-2.0-flash-lite-001", "gemini-2.5-flash-lite-preview-06-17", "gemini-2.5-flash-lite", "gemini-2.0-flash-001", "llama-4-scout-17b-16e-instruct-maas", "qwen3-235b-a22b-instruct-2507-maas", "gemini-2.5-flash", "gemini-2.5-flash-image-preview", "llama-4-maverick-17b-128e-instruct-maas", "llama-3.3-70b-instruct-maas", "claude-3-5-haiku@20241022", "qwen3-coder-480b-a35b-instruct-maas", "gemini-1.5-pro-002", "gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-preview-05-06", "gemini-2.5-pro", "deepseek-r1-0528-maas", "claude-3-7-sonnet@20250219", "claude-3-5-sonnet-v2@20241022", "claude-sonnet-4@20250514", "claude-opus-4-1@20250805", "claude-opus-4@20250514", "claude-3-haiku@20240307", "claude-3-5-sonnet@20240620", "claude-3-opus@20240229", "gemini-2.5-flash-lite-preview-09-2025", "gemini-2.5-flash-preview-09-2025", "gemini-2.5-flash-image", "claude-sonnet-4-5@20250929", "claude-haiku-4-5@20251001", "minimax/minimax-m2-maas", "gemini-3-pro-preview", "gemini-3-pro-image-preview", "claude-opus-4-5@20251101" ], "sendClientIp": false, "pricingStrategy": "gemini" }, "provider_display_name": "Google Vertex", "provider_slug": "google-vertex", "provider_model_id": "gemini-2.0-flash-exp", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "seed", "response_format", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": true, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 55, "canPublish": false, "termsOfServiceURL": "https://cloud.google.com/terms/", "privacyPolicyURL": "https://cloud.google.com/terms/cloud-privacy-notice", "requiresUserIDs": true }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "gemini:prompt_tokens": "0", "gemini:reasoning_tokens": "0", "gemini:cache_read_tokens": "0", "gemini:completion_tokens": "0", "gemini:text_input_tokens": "0", "gemini:audio_input_tokens": "0", "gemini:image_input_tokens": "0", "gemini:video_input_tokens": "0", "gemini:cache_read_text_tokens": "0", "gemini:cache_read_audio_tokens": "0", "gemini:cache_read_image_tokens": "0", "gemini:cache_read_video_tokens": "0", "gemini:cache_write_storage_hours": "0", "gemini:cache_read_tokens_high_context": "0", "gemini:cache_read_text_tokens_high_context": "0", "gemini:cache_read_audio_tokens_high_context": "0", "gemini:cache_read_image_tokens_high_context": "0", "gemini:cache_read_video_tokens_high_context": "0", "gemini:informational_cache_write_tokens_count": 0 }, "pricing_version_id": "66d10a89-12f4-4443-8fe8-436118617f33", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": "2026-03-03" } }, { "slug": "amazon/nova-lite-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-05T22:22:43.403315+00:00", "hf_updated_at": null, "name": "Amazon: Nova Lite 1.0", "short_name": "Nova Lite 1.0", "author": "amazon", "description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\n\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.", "model_version_group_id": null, "context_length": 300000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "amazon/nova-lite-v1", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "72eda073-d180-4482-8e4f-81051cb66f7e", "name": "Amazon Bedrock | amazon/nova-lite-v1", "context_length": 300000, "model": { "slug": "amazon/nova-lite-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-05T22:22:43.403315+00:00", "hf_updated_at": null, "name": "Amazon: Nova Lite 1.0", "short_name": "Nova Lite 1.0", "author": "amazon", "description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\n\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.", "model_version_group_id": null, "context_length": 300000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "amazon/nova-lite-v1", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "amazon/nova-lite-v1", "model_variant_permaslug": "amazon/nova-lite-v1", "adapter_name": "AmazonBedrockConverseAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.amazon.nova-lite-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 5120, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.00000006", "completion": "0.00000024", "image": "0.00009", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "amazon/nova-pro-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-05T22:05:03.587216+00:00", "hf_updated_at": null, "name": "Amazon: Nova Pro 1.0", "short_name": "Nova Pro 1.0", "author": "amazon", "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\n\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.\n\n**NOTE**: Video input is not supported at this time.", "model_version_group_id": null, "context_length": 300000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "amazon/nova-pro-v1", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "959381a4-8054-450f-9daf-5fcab64ba9aa", "name": "Amazon Bedrock | amazon/nova-pro-v1", "context_length": 300000, "model": { "slug": "amazon/nova-pro-v1", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-05T22:05:03.587216+00:00", "hf_updated_at": null, "name": "Amazon: Nova Pro 1.0", "short_name": "Nova Pro 1.0", "author": "amazon", "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\n\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.\n\n**NOTE**: Video input is not supported at this time.", "model_version_group_id": null, "context_length": 300000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Nova", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "amazon/nova-pro-v1", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "amazon/nova-pro-v1", "model_variant_permaslug": "amazon/nova-pro-v1", "adapter_name": "AmazonBedrockConverseAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": null }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.amazon.nova-pro-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 5120, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.0000008", "completion": "0.0000032", "image": "0.0012", "request": "0", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [], "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o-2024-11-20", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-20T18:33:14.771895+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-11-20)", "short_name": "GPT-4o (2024-11-20)", "author": "openai", "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-11-20", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "3e86b7c5-bffe-4b60-a3dd-b36451978775", "name": "OpenAI | openai/gpt-4o-2024-11-20", "context_length": 128000, "model": { "slug": "openai/gpt-4o-2024-11-20", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-20T18:33:14.771895+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-11-20)", "short_name": "GPT-4o (2024-11-20)", "author": "openai", "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-11-20", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o-2024-11-20", "model_variant_permaslug": "openai/gpt-4o-2024-11-20", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o-2024-11-20", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000025", "completion": "0.00001", "input_cache_read": "0.00000125", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai:prompt_tokens": 0.0000025, "openai:completion_tokens": 0.00001, "openai:cached_prompt_tokens": 0.00000125 }, "pricing_version_id": "8359b48b-204e-47a6-aea1-737dba83e20c", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/pixtral-large-2411", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-19T00:49:48.873161+00:00", "hf_updated_at": null, "name": "Mistral: Pixtral Large 2411", "short_name": "Pixtral Large 2411", "author": "mistralai", "description": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images.\n\nThe model is available under the Mistral Research License (MRL) for research and educational use, and the Mistral Commercial License for experimentation, testing, and production for commercial purposes.\n\n", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/pixtral-large-2411", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "1a41639e-c1cf-422e-a871-27bc67f03928", "name": "Mistral | mistralai/pixtral-large-2411", "context_length": 131072, "model": { "slug": "mistralai/pixtral-large-2411", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-19T00:49:48.873161+00:00", "hf_updated_at": null, "name": "Mistral: Pixtral Large 2411", "short_name": "Pixtral Large 2411", "author": "mistralai", "description": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images.\n\nThe model is available under the Mistral Research License (MRL) for research and educational use, and the Mistral Commercial License for experimentation, testing, and production for commercial purposes.\n\n", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/pixtral-large-2411", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/pixtral-large-2411", "model_variant_permaslug": "mistralai/pixtral-large-2411", "adapter_name": "MistralAdapter", "provider_name": "Mistral", "provider_info": { "name": "Mistral", "displayName": "Mistral", "slug": "mistral", "baseUrl": "https://api.mistral.ai/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "headquarters": "FR", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "MistralAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.mistral.ai/", "byokEnabled": true, "icon": { "url": "/images/icons/Mistral.png" }, "ignoredProviderModels": [ "mistral-moderation-2411-all", "voxtral-mini-2507", "voxtral-small-2507", "voxtral-mini-transcribe-2507", "mistral-medium", "mistral-tiny", "mistral-tiny-2312", "open-mistral-nemo", "mistral-tiny-2407", "open-mixtral-8x7b", "mistral-small", "mistral-small-2312", "open-mixtral-8x22b-2404", "mistral-large-pixtral-2411", "codestral-2412", "codestral-2411-rc5", "pixtral-12b", "mistral-moderation-2411", "mistral-ocr-2503", "mistral-ocr-2505", "mistral-saba-2502", "open-mixtral-8x22b", "mistral-large-2407", "magistral-medium-2507", "mistral-embed", "codestral-embed", "codestral-2501", "mistral-small-2501", "mistral-ocr-2512", "labs-devstral-small-2512" ], "sendClientIp": false, "pricingStrategy": "mistral" }, "provider_display_name": "Mistral", "provider_slug": "mistral", "provider_model_id": "pixtral-large-2411", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://mistral.ai/terms/#terms-of-use", "privacyPolicyURL": "https://mistral.ai/terms/#privacy-policy" }, "pricing": { "prompt": "0.000002", "completion": "0.000006", "discount": 0 }, "variable_pricings": [], "pricing_json": { "mistral:prompt_tokens": 0.000002, "mistral:completion_tokens": 0.000006 }, "pricing_version_id": "b80bc0f8-6b6c-4dd4-9205-041df98e8a5f", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-3.5-haiku", "hf_slug": null, "updated_at": "2025-12-05T21:54:21.40359+00:00", "created_at": "2024-11-04T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Haiku", "short_name": "Claude 3.5 Haiku", "author": "anthropic", "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).", "model_version_group_id": "028ec497-a034-40fd-81fe-f51d0a0c640c", "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-5-haiku", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "50d15f84-5009-4962-a843-90401118ddd2", "name": "Amazon Bedrock | anthropic/claude-3-5-haiku", "context_length": 200000, "model": { "slug": "anthropic/claude-3.5-haiku", "hf_slug": null, "updated_at": "2025-12-05T21:54:21.40359+00:00", "created_at": "2024-11-04T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Haiku", "short_name": "Claude 3.5 Haiku", "author": "anthropic", "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).", "model_version_group_id": "028ec497-a034-40fd-81fe-f51d0a0c640c", "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-5-haiku", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "amazon-bedrock", "google-vertex", "anthropic" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-3.5-haiku", "model_variant_permaslug": "anthropic/claude-3-5-haiku", "adapter_name": "AmazonBedrockInvokeAnthropicAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.0000008", "completion": "0.000004", "input_cache_read": "0.00000008", "input_cache_write": "0.000001", "web_search": "0.01", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 8e-7, "anthropic:web_search_calls": 0.01, "anthropic:cache_read_tokens": 8e-8, "anthropic:completion_tokens": 0.000004, "anthropic:cache_write_1h_tokens": 0.0000016, "anthropic:cache_write_5m_tokens": 0.000001 }, "pricing_version_id": "dcdd1da5-3a78-4f57-8122-d38c1110c682", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-3.5-sonnet", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-10-22T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Sonnet", "short_name": "Claude 3.5 Sonnet", "author": "anthropic", "description": "New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3.5-sonnet", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "d4fb79bd-9786-4932-af81-b83040e9f4e4", "name": "Amazon Bedrock | anthropic/claude-3.5-sonnet", "context_length": 200000, "model": { "slug": "anthropic/claude-3.5-sonnet", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-10-22T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Sonnet", "short_name": "Claude 3.5 Sonnet", "author": "anthropic", "description": "New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3.5-sonnet", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-3.5-sonnet", "model_variant_permaslug": "anthropic/claude-3.5-sonnet", "adapter_name": "AmazonBedrockInvokeAnthropicAdapter", "provider_name": "Amazon Bedrock", "provider_info": { "name": "Amazon Bedrock", "displayName": "Amazon Bedrock", "slug": "amazon-bedrock", "baseUrl": "not_used", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "dummy-value" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": false, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AmazonBedrockConverseAdapter", "isMultipartSupported": true, "statusPageUrl": "https://health.aws.amazon.com/health/status", "byokEnabled": true, "icon": { "url": "/images/icons/Bedrock.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Amazon Bedrock", "provider_slug": "amazon-bedrock", "provider_model_id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": false, "max_prompt_tokens": null, "max_completion_tokens": 8192, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://aws.amazon.com/service-terms/", "privacyPolicyURL": "https://aws.amazon.com/privacy" }, "pricing": { "prompt": "0.000006", "completion": "0.00003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 0.000006, "anthropic:completion_tokens": 0.00003 }, "pricing_version_id": "eb96ddba-9cd5-4a4b-bb70-4f88db92ecb1", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "meta-llama/llama-3.2-11b-vision-instruct", "hf_slug": "meta-llama/Llama-3.2-11B-Vision-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-09-25T00:00:00+00:00", "hf_updated_at": null, "name": "Meta: Llama 3.2 11B Vision Instruct", "short_name": "Llama 3.2 11B Vision Instruct", "author": "meta-llama", "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis.\n\nIts ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama3", "instruct_type": "llama3", "default_system": null, "default_stops": [ "<|eot_id|>", "<|end_of_text|>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-3.2-11b-vision-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "4a07b512-e030-412d-b1d6-39773a8b8dcf", "name": "DeepInfra | meta-llama/llama-3.2-11b-vision-instruct", "context_length": 131072, "model": { "slug": "meta-llama/llama-3.2-11b-vision-instruct", "hf_slug": "meta-llama/Llama-3.2-11B-Vision-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-09-25T00:00:00+00:00", "hf_updated_at": null, "name": "Meta: Llama 3.2 11B Vision Instruct", "short_name": "Llama 3.2 11B Vision Instruct", "author": "meta-llama", "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis.\n\nIts ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama3", "instruct_type": "llama3", "default_system": null, "default_stops": [ "<|eot_id|>", "<|end_of_text|>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-3.2-11b-vision-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "meta-llama/llama-3.2-11b-vision-instruct", "model_variant_permaslug": "meta-llama/llama-3.2-11b-vision-instruct", "adapter_name": "DeepInfraAdapter", "provider_name": "DeepInfra", "provider_info": { "name": "DeepInfra", "displayName": "DeepInfra", "slug": "deepinfra", "baseUrl": "https://api.deepinfra.com/v1/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}", "org_38GSfr7NVq111kyg6iXh1TTpKuz" ], "adapterName": "DeepInfraAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.deepinfra.com/", "byokEnabled": true, "icon": { "url": "/images/icons/DeepInfra.webp" }, "ignoredProviderModels": [ "anthropic/claude-4-opus", "anthropic/claude-4-sonnet", "deepseek-ai/DeepSeek-R1-0528-Turbo", "meta-llama/Llama-2-70b-chat-hf", "mistralai/Mixtral-8x22B-Instruct-v0.1", "google/gemma-1.1-7b-it", "microsoft/Phi-3-medium-4k-instruct", "google/gemma-2-27b-it", "microsoft/WizardLM-2-7B", "mattshumer/Reflection-Llama-3.1-70B", "Sao10K/L3-8B-Lunaris-v1", "openbmb/MiniCPM-Llama3-V-2_5", "Qwen/QVQ-72B-Preview", "deepinfra/airoboros-70b", "Qwen/QwQ-32B-Preview", "Phind/Phind-CodeLlama-34B-v2", "lizpreciatior/lzlv_70b_fp16_hf", "mistralai/Mistral-7B-Instruct-v0.2", "cognitivecomputations/dolphin-2.6-mixtral-8x7b", "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "Qwen/Qwen2-72B-Instruct", "Qwen/Qwen2-7B-Instruct", "google/gemma-2-9b-it", "Sao10K/L3-70B-Euryale-v2.1", "google/codegemma-7b-it", "mistralai/Mistral-7B-Instruct-v0.1", "KoboldAI/LLaMA2-13B-Tiefighter", "meta-llama/Llama-2-13b-chat-hf", "openchat/openchat_3.5", "openchat/openchat-3.6-8b", "bigcode/starcoder2-15b-instruct-v0.1", "Gryphe/MythoMax-L2-13b-turbo", "Austism/chronos-hermes-13b-v2", "Qwen/Qwen2.5-Coder-7B", "moonshotai/Kimi-K2-Instruct", "google/gemini-1.5-flash", "google/gemini-2.5-flash", "google/gemini-2.0-flash-001", "anthropic/claude-3-7-sonnet-latest", "google/gemini-1.5-flash-8b", "google/gemini-2.5-pro", "NovaSky-AI/Sky-T1-32B-Preview", "allenai/olmOCR-7B-0725-FP8", "allenai/olmOCR-7B-0825", "deepseek-ai/DeepSeek-V3-0324-Turbo", "PaddlePaddle/PaddleOCR-VL-0.9B", "allenai/olmOCR-7B-1025", "allenai/olmOCR-2-7B-1025", "allenai/olmOCR-2", "deepseek-ai/DeepSeek-OCR", "meta-llama/Llama-3.2-1B-Instruct", "sentence-transformers/clip-ViT-B-32-multilingual-v1", "shibing624/text2vec-base-chinese", "sentence-transformers/clip-ViT-B-32", "BAAI/bge-en-icl", "Qwen/Qwen3-Embedding-8B-batch", "Qwen/Qwen3-Embedding-4B-batch", "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "meta-llama/Meta-Llama-3.1-405B-Instruct", "BAAI/bge-m3-multi", "google/embeddinggemma-300m", "Qwen/Qwen3-Embedding-0.6B-batch", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "microsoft/Phi-4-multimodal-instruct", "deepseek-ai/DeepSeek-V3.2-Exp", "meta-llama/Llama-3.2-90B-Vision-Instruct", "meta-llama/Meta-Llama-3-70B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "DeepInfra", "provider_slug": "deepinfra/fp8", "provider_model_id": "meta-llama/Llama-3.2-11B-Vision-Instruct", "quantization": "fp8", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "repetition_penalty", "top_k", "seed", "min_p", "response_format" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://deepinfra.com/terms", "privacyPolicyURL": "https://deepinfra.com/privacy" }, "pricing": { "prompt": "0.000000049", "completion": "0.000000049", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.000000049", "openai:completion_tokens": "0.000000049" }, "pricing_version_id": "66e3a91d-e4dd-4721-b500-9f23d2365917", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "mistralai/pixtral-12b", "hf_slug": "mistralai/Pixtral-12B-2409", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-09-10T00:00:00+00:00", "hf_updated_at": null, "name": "Mistral: Pixtral 12B", "short_name": "Pixtral 12B", "author": "mistralai", "description": "The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/pixtral-12b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "b550f7af-571a-45fd-b442-b3327afaf38c", "name": "Hyperbolic | mistralai/pixtral-12b", "context_length": 32768, "model": { "slug": "mistralai/pixtral-12b", "hf_slug": "mistralai/Pixtral-12B-2409", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-09-10T00:00:00+00:00", "hf_updated_at": null, "name": "Mistral: Pixtral 12B", "short_name": "Pixtral 12B", "author": "mistralai", "description": "The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "mistralai/pixtral-12b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": { "temperature": 0.3 }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "mistralai/pixtral-12b", "model_variant_permaslug": "mistralai/pixtral-12b", "adapter_name": "HyperbolicAdapter", "provider_name": "Hyperbolic", "provider_info": { "name": "Hyperbolic", "displayName": "Hyperbolic", "slug": "hyperbolic", "baseUrl": "https://api.hyperbolic.xyz/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://hyperbolic.xyz/terms", "privacyPolicyURL": "https://hyperbolic.xyz/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "HyperbolicAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://hyperbolic.xyz/&size=256" }, "ignoredProviderModels": [ "Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Hyperbolic", "provider_slug": "hyperbolic/bf16", "provider_model_id": "mistralai/Pixtral-12B-2409", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "logit_bias", "top_k", "min_p", "repetition_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://hyperbolic.xyz/terms", "privacyPolicyURL": "https://hyperbolic.xyz/privacy" }, "pricing": { "prompt": "0.0000001", "completion": "0.0000001", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000001", "openai:completion_tokens": "0.0000001" }, "pricing_version_id": "bd22699d-f1d8-49fe-afc3-99a0936757d6", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen-2.5-vl-7b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-7B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-28T00:00:00+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5-VL 7B Instruct (free)", "short_name": "Qwen2.5-VL 7B Instruct (free)", "author": "qwen", "description": "Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Understanding videos of 20min+: Qwen2.5-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-2-vl-7b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "77ef6e4c-601d-4bd6-b168-c88a5b44a792", "name": "ModelRun | qwen/qwen-2-vl-7b-instruct:free", "context_length": 32768, "model": { "slug": "qwen/qwen-2.5-vl-7b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-7B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-28T00:00:00+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5-VL 7B Instruct", "short_name": "Qwen2.5-VL 7B Instruct", "author": "qwen", "description": "Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Understanding videos of 20min+: Qwen2.5-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-2-vl-7b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen-2.5-vl-7b-instruct:free", "model_variant_permaslug": "qwen/qwen-2-vl-7b-instruct:free", "adapter_name": "OpenAIAdapter", "provider_name": "ModelRun", "provider_info": { "name": "ModelRun", "displayName": "ModelRun", "slug": "modelrun", "baseUrl": "https://api.runmodelrun.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.runmodelrun.com/TOS.html", "privacyPolicyURL": "https://www.runmodelrun.com/privacy-policy.html" }, "headquarters": "US", "datacenters": [ "US" ], "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [], "owners": [], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": false, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://api.runmodelrun.com&size=256" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "ModelRun", "provider_slug": "modelrun", "provider_model_id": "Qwen/Qwen2.5-VL-7B-Instruct", "quantization": "unknown", "variant": "free", "is_free": true, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "presence_penalty", "repetition_penalty", "frequency_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.runmodelrun.com/TOS.html", "privacyPolicyURL": "https://www.runmodelrun.com/privacy-policy.html" }, "pricing": { "prompt": "0", "completion": "0", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": 0, "openai:completion_tokens": 0 }, "pricing_version_id": "22606844-5b89-4cf3-9031-5175f3f83d81", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supports_input_audio": false }, "provider_region": null, "deprecation_date": null } }, { "slug": "qwen/qwen-2.5-vl-7b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-7B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-28T00:00:00+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5-VL 7B Instruct", "short_name": "Qwen2.5-VL 7B Instruct", "author": "qwen", "description": "Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Understanding videos of 20min+: Qwen2.5-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-2-vl-7b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": { "id": "fae5bc3c-f799-4657-8d05-3cf6f489ed0c", "name": "Hyperbolic | qwen/qwen-2-vl-7b-instruct", "context_length": 32768, "model": { "slug": "qwen/qwen-2.5-vl-7b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-7B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-28T00:00:00+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5-VL 7B Instruct", "short_name": "Qwen2.5-VL 7B Instruct", "author": "qwen", "description": "Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Understanding videos of 20min+: Qwen2.5-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen-2-vl-7b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null }, "model_variant_slug": "qwen/qwen-2.5-vl-7b-instruct", "model_variant_permaslug": "qwen/qwen-2-vl-7b-instruct", "adapter_name": "HyperbolicAdapter", "provider_name": "Hyperbolic", "provider_info": { "name": "Hyperbolic", "displayName": "Hyperbolic", "slug": "hyperbolic", "baseUrl": "https://api.hyperbolic.xyz/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://hyperbolic.xyz/terms", "privacyPolicyURL": "https://hyperbolic.xyz/privacy" }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "HyperbolicAdapter", "isMultipartSupported": true, "statusPageUrl": null, "byokEnabled": true, "icon": { "url": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://hyperbolic.xyz/&size=256" }, "ignoredProviderModels": [ "Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Hyperbolic", "provider_slug": "hyperbolic/bf16", "provider_model_id": "Qwen/Qwen2.5-VL-7B-Instruct", "quantization": "bf16", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": null, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "seed", "logit_bias", "top_k", "min_p", "repetition_penalty" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://hyperbolic.xyz/terms", "privacyPolicyURL": "https://hyperbolic.xyz/privacy" }, "pricing": { "prompt": "0.0000002", "completion": "0.0000002", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": "0.0000002", "openai:completion_tokens": "0.0000002" }, "pricing_version_id": "92bd83cb-246a-4525-b1b2-497cb23f093e", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true }, "supported_parameters": {} }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/chatgpt-4o-latest", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-14T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: ChatGPT-4o", "short_name": "ChatGPT-4o", "author": "openai", "description": "OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/chatgpt-4o-latest", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "aff4b825-af10-4633-9ab2-9ac68c547988", "name": "OpenAI | openai/chatgpt-4o-latest", "context_length": 128000, "model": { "slug": "openai/chatgpt-4o-latest", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-14T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: ChatGPT-4o", "short_name": "ChatGPT-4o", "author": "openai", "description": "OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/chatgpt-4o-latest", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/chatgpt-4o-latest", "model_variant_permaslug": "openai/chatgpt-4o-latest", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "chatgpt-4o-latest", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000005", "completion": "0.000015", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": 0.000005, "openai:completion_tokens": 0.000015 }, "pricing_version_id": "7ba48c60-6be4-495f-beb5-c2a7b5b22639", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": false, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o-2024-08-06", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-06T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-08-06)", "short_name": "GPT-4o (2024-08-06)", "author": "openai", "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-08-06", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "59ea8d2a-1b1b-47f1-83de-a358a724caeb", "name": "Azure | openai/gpt-4o-2024-08-06", "context_length": 128000, "model": { "slug": "openai/gpt-4o-2024-08-06", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-06T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-08-06)", "short_name": "GPT-4o (2024-08-06)", "author": "openai", "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-08-06", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o-2024-08-06", "model_variant_permaslug": "openai/gpt-4o-2024-08-06", "adapter_name": "AzureOpenAIAdapter", "provider_name": "Azure", "provider_info": { "name": "Azure", "displayName": "Azure", "slug": "azure", "baseUrl": "https://openrouter-east-us-2.openai.azure.com/openai", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true", "privacyPolicyURL": "https://www.microsoft.com/en-us/privacy/privacystatement" }, "headquarters": "US", "regionOverrides": { "europe": { "baseUrl": "https://openrouter-eu-resource.cognitiveservices.azure.com/openai" } }, "hasChatCompletions": true, "hasCompletions": false, "isAbortable": true, "moderationRequired": false, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AzureOpenAIAdapter", "isMultipartSupported": false, "statusPageUrl": "https://status.azure.com/", "byokEnabled": true, "icon": { "url": "/images/icons/Azure.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "Azure", "provider_slug": "azure", "provider_model_id": "gpt-4o", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "seed", "logit_bias", "logprobs", "top_logprobs", "response_format", "structured_outputs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": false, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": false, "canPublish": false, "termsOfServiceURL": "https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true", "privacyPolicyURL": "https://www.microsoft.com/en-us/privacy/privacystatement" }, "pricing": { "prompt": "0.0000025", "completion": "0.00001", "image": "0.003613", "request": "0", "input_cache_read": "0.00000125", "web_search": "0", "internal_reasoning": "0", "image_output": "0", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai:prompt_tokens": 0.0000025, "openai:completion_tokens": 0.00001, "openai:cached_prompt_tokens": 0.00000125 }, "pricing_version_id": "35fabd0d-b247-41ac-8e48-9f3ef3031f55", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": false, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o-mini-2024-07-18", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-07-18T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o-mini (2024-07-18)", "short_name": "GPT-4o-mini (2024-07-18)", "author": "openai", "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-mini-2024-07-18", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15", "name": "OpenAI | openai/gpt-4o-mini-2024-07-18", "context_length": 128000, "model": { "slug": "openai/gpt-4o-mini-2024-07-18", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-07-18T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o-mini (2024-07-18)", "short_name": "GPT-4o-mini (2024-07-18)", "author": "openai", "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-mini-2024-07-18", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o-mini-2024-07-18", "model_variant_permaslug": "openai/gpt-4o-mini-2024-07-18", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o-mini-2024-07-18", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000015", "completion": "0.0000006", "input_cache_read": "0.000000075", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.03" }, { "type": "search-threshold", "threshold": "medium", "request": "0.0275" }, { "type": "search-threshold", "threshold": "low", "request": "0.025" } ], "pricing_json": { "openai:prompt_tokens": 1.5e-7, "openai:completion_tokens": 6e-7, "openai:cached_prompt_tokens": 7.5e-8 }, "pricing_version_id": "bb978658-5598-4ad9-8224-e8e5d57794cd", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o-mini", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-07-18T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o-mini", "short_name": "GPT-4o-mini", "author": "openai", "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-mini", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "77e40332-6f2a-4c48-bc14-e44596b30ce2", "name": "OpenAI | openai/gpt-4o-mini", "context_length": 128000, "model": { "slug": "openai/gpt-4o-mini", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-07-18T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o-mini", "short_name": "GPT-4o-mini", "author": "openai", "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-mini", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o-mini", "model_variant_permaslug": "openai/gpt-4o-mini", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o-mini", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000015", "completion": "0.0000006", "input_cache_read": "0.000000075", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.03" }, { "type": "search-threshold", "threshold": "medium", "request": "0.0275" }, { "type": "search-threshold", "threshold": "low", "request": "0.025" } ], "pricing_json": { "openai:prompt_tokens": 1.5e-7, "openai:completion_tokens": 6e-7, "openai:cached_prompt_tokens": 7.5e-8 }, "pricing_version_id": "496e0c4b-dfc8-40e3-97e1-d0eeeab62195", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o-2024-05-13", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-05-13)", "short_name": "GPT-4o (2024-05-13)", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-05-13", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "3d6584e7-a2bb-48d6-903d-24e3d90e7e55", "name": "OpenAI | openai/gpt-4o-2024-05-13", "context_length": 128000, "model": { "slug": "openai/gpt-4o-2024-05-13", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (2024-05-13)", "short_name": "GPT-4o (2024-05-13)", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o-2024-05-13", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o-2024-05-13", "model_variant_permaslug": "openai/gpt-4o-2024-05-13", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o-2024-05-13", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 4096, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000005", "completion": "0.000015", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai:prompt_tokens": 0.000005, "openai:completion_tokens": 0.000015 }, "pricing_version_id": "dab5f507-2c79-4281-bc39-5346d8549075", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o", "short_name": "GPT-4o", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "452a72a0-2c24-4e31-98cb-d6cc1084fb99", "name": "OpenAI | openai/gpt-4o", "context_length": 128000, "model": { "slug": "openai/gpt-4o", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o", "short_name": "GPT-4o", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o", "model_variant_permaslug": "openai/gpt-4o", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 16384, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.0000025", "completion": "0.00001", "input_cache_read": "0.00000125", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai:prompt_tokens": 0.0000025, "openai:completion_tokens": 0.00001, "openai:cached_prompt_tokens": 0.00000125 }, "pricing_version_id": "9a09c5e1-25e5-4027-ac71-8ada7a7a80b9", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4o", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o (extended)", "short_name": "GPT-4o (extended)", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "3f4c883a-bd8b-4e01-ac1b-25cc9a17dd61", "name": "OpenAI | openai/gpt-4o:extended", "context_length": 128000, "model": { "slug": "openai/gpt-4o", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4o", "short_name": "GPT-4o", "author": "openai", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal", "model_version_group_id": "76e36b33-358e-477a-be24-09f954fcea74", "context_length": 128000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4o", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4o:extended", "model_variant_permaslug": "openai/gpt-4o:extended", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4o-64k-output-alpha", "quantization": "unknown", "variant": "extended", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 64000, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "web_search_options", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.000006", "completion": "0.000018", "discount": 0 }, "variable_pricings": [ { "type": "search-threshold", "threshold": "high", "request": "0.05" }, { "type": "search-threshold", "threshold": "medium", "request": "0.035" }, { "type": "search-threshold", "threshold": "low", "request": "0.03" } ], "pricing_json": { "openai:prompt_tokens": 0.000006, "openai:completion_tokens": 0.000018 }, "pricing_version_id": "1a91197b-4d58-49bd-9658-0563b513b7da", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openai/gpt-4-turbo", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-04-09T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4 Turbo", "short_name": "GPT-4 Turbo", "author": "openai", "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4-turbo", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "da16824f-3ba0-43a1-86f8-a6131837f457", "name": "OpenAI | openai/gpt-4-turbo", "context_length": 128000, "model": { "slug": "openai/gpt-4-turbo", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-04-09T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4 Turbo", "short_name": "GPT-4 Turbo", "author": "openai", "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4-turbo", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "openai/gpt-4-turbo", "model_variant_permaslug": "openai/gpt-4-turbo", "adapter_name": "OpenAIAdapter", "provider_name": "OpenAI", "provider_info": { "name": "OpenAI", "displayName": "OpenAI", "slug": "openai", "baseUrl": "https://api.openai.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "OpenAIAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.openai.com/", "byokEnabled": true, "icon": { "url": "/images/icons/OpenAI.svg", "className": "invert-0 dark:invert" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "openai_chat_completions" }, "provider_display_name": "OpenAI", "provider_slug": "openai", "provider_model_id": "gpt-4-turbo", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 4096, "max_tokens_per_image": null, "supported_parameters": [ "seed", "max_tokens", "response_format", "structured_outputs", "temperature", "top_p", "stop", "frequency_penalty", "presence_penalty", "logit_bias", "logprobs", "top_logprobs", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "canPublish": false, "termsOfServiceURL": "https://openai.com/policies/row-terms-of-use/", "privacyPolicyURL": "https://openai.com/policies/privacy-policy/", "requiresUserIDs": true }, "pricing": { "prompt": "0.00001", "completion": "0.00003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "openai:prompt_tokens": 0.00001, "openai:completion_tokens": 0.00003 }, "pricing_version_id": "48751c0f-27b9-45d7-9b9a-ec343acdf97b", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "anthropic/claude-3-haiku", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-03-13T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3 Haiku", "short_name": "Claude 3 Haiku", "author": "anthropic", "description": "Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal", "model_version_group_id": "028ec497-a034-40fd-81fe-f51d0a0c640c", "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-haiku", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": { "id": "8661a1db-b0cf-4eb2-ba04-c2a79f698682", "name": "Anthropic | anthropic/claude-3-haiku", "context_length": 200000, "model": { "slug": "anthropic/claude-3-haiku", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-03-13T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3 Haiku", "short_name": "Claude 3 Haiku", "author": "anthropic", "description": "Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal", "model_version_group_id": "028ec497-a034-40fd-81fe-f51d0a0c640c", "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-haiku", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null }, "model_variant_slug": "anthropic/claude-3-haiku", "model_variant_permaslug": "anthropic/claude-3-haiku", "adapter_name": "AnthropicMessageAdapter", "provider_name": "Anthropic", "provider_info": { "name": "Anthropic", "displayName": "Anthropic", "slug": "anthropic", "baseUrl": "https://api.anthropic.com/v1", "dataPolicy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.anthropic.com/legal/commercial-terms", "privacyPolicyURL": "https://www.anthropic.com/legal/privacy", "requiresUserIDs": true }, "headquarters": "US", "regionOverrides": {}, "hasChatCompletions": true, "hasCompletions": true, "isAbortable": true, "moderationRequired": true, "editors": [ "{}" ], "owners": [ "{}" ], "adapterName": "AnthropicMessageAdapter", "isMultipartSupported": true, "statusPageUrl": "https://status.anthropic.com/", "byokEnabled": true, "icon": { "url": "/images/icons/Anthropic.svg" }, "ignoredProviderModels": [], "sendClientIp": false, "pricingStrategy": "anthropic" }, "provider_display_name": "Anthropic", "provider_slug": "anthropic", "provider_model_id": "claude-3-haiku-20240307", "quantization": "unknown", "variant": "standard", "is_free": false, "can_abort": true, "max_prompt_tokens": null, "max_completion_tokens": 4096, "max_tokens_per_image": null, "supported_parameters": [ "max_tokens", "temperature", "top_p", "top_k", "stop", "tools", "tool_choice" ], "is_byok": false, "moderation_required": true, "data_policy": { "training": false, "trainingOpenRouter": false, "retainsPrompts": true, "retentionDays": 30, "canPublish": false, "termsOfServiceURL": "https://www.anthropic.com/legal/commercial-terms", "privacyPolicyURL": "https://www.anthropic.com/legal/privacy", "requiresUserIDs": true }, "pricing": { "prompt": "0.00000025", "completion": "0.00000125", "input_cache_read": "0.00000003", "input_cache_write": "0.0000003", "discount": 0 }, "variable_pricings": [], "pricing_json": { "anthropic:prompt_tokens": 2.5e-7, "anthropic:cache_read_tokens": 3e-8, "anthropic:completion_tokens": 0.00000125, "anthropic:cache_write_1h_tokens": 5e-7, "anthropic:cache_write_5m_tokens": 3e-7 }, "pricing_version_id": "6e785387-5305-4e6a-84e2-76c9ab02b414", "is_hidden": false, "is_deranked": false, "is_disabled": false, "supports_tool_parameters": true, "supports_reasoning": false, "supports_multipart": true, "limit_rpm": null, "limit_rpd": null, "limit_rpm_cf": null, "has_completions": true, "has_chat_completions": true, "features": { "supports_tool_choice": { "literal_none": true, "literal_auto": true, "literal_required": true, "type_function": true } }, "provider_region": null, "deprecation_date": null } }, { "slug": "openrouter/bert-nebulon-alpha", "hf_slug": "", "updated_at": "2025-12-02T15:25:47.01144+00:00", "created_at": "2025-11-24T17:24:18+00:00", "hf_updated_at": null, "name": "Bert-Nebulon Alpha", "short_name": "Bert-Nebulon Alpha", "author": "openrouter", "description": "This model was an early testing version of Mistral Large 3. Try the official launch of Mistral Large 3 [here](/mistralai/mistral-large-2512)\n\nThis is a cloaked model provided to the community to gather feedback. A general-purpose multimodal model (text/image in, text out) designed for reliability, long-context comprehension, and adaptive logic. It is engineered for production-grade assistants, retrieval-augmented systems, science workloads, and complex agentic workflows.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": "", "routing_error_message": "Bert-Nebulon Alpha was a stealth model revealed on December 2nd as an early testing version of Mistral Large 3. Find it here: {{SITE_UR}}/mistralai/mistral-large-2512", "permaslug": "openrouter/bert-nebulon-alpha", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.0645, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "text", "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/sherlock-dash-alpha", "hf_slug": "", "updated_at": "2025-11-19T23:50:42.801865+00:00", "created_at": "2025-11-15T17:49:49+00:00", "hf_updated_at": null, "name": "Sherlock Dash Alpha", "short_name": "Sherlock Dash Alpha", "author": "openrouter", "description": "This model was an early snapshot of Grok 4.1 Fast with reasoning disabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast)\n\nThis is a cloaked model provided to the community to gather feedback. A frontier non-reasoning model that excels at tool calling, with a 1.8M context window and multimodal support.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 1840000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "This model was an early snapshot of Grok 4.1 Fast with reasoning disabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast)\n\nAll prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": "", "routing_error_message": null, "permaslug": "openrouter/sherlock-dash-alpha", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/sherlock-think-alpha", "hf_slug": "", "updated_at": "2025-11-20T02:01:49.950758+00:00", "created_at": "2025-11-15T17:49:46+00:00", "hf_updated_at": null, "name": "Sherlock Think Alpha", "short_name": "Sherlock Think Alpha", "author": "openrouter", "description": "This model was an early snapshot of Grok 4.1 Fast with reasoning enabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast)\n\nThis is a cloaked model provided to the community to gather feedback. A frontier reasoning model that excels at tool calling, with a 1.8M context window and multimodal support.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 1840000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "This model was an early snapshot of Grok 4.1 Fast with reasoning enabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast)\n\nAll prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": "", "routing_error_message": null, "permaslug": "openrouter/sherlock-think-alpha", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": 0.7, "top_p": 0.95, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/polaris-alpha", "hf_slug": "", "updated_at": "2025-11-19T23:49:14.889425+00:00", "created_at": "2025-11-06T17:55:07.695182+00:00", "hf_updated_at": null, "name": "Polaris Alpha", "short_name": "Polaris Alpha", "author": "openrouter", "description": "This model was an early snapshot of GPT-5.1 with reasoning effort set to minimal. Try the official launch of GPT-5.1 [here](/openai/gpt-5.1)\n\nThis is a cloaked model provided to the community to gather feedback. A powerful, general-purpose model that excels across real-world tasks, with standout performance in coding, tool calling, and instruction following.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "This model was an early snapshot of GPT-5.1 with reasoning effort set to minimal. Try the official launch of GPT-5.1 here: /openai/gpt-5.1\n\nAll prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": "", "routing_error_message": null, "permaslug": "openrouter/polaris-alpha", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "chat_template_config": {} }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": "reasoning", "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/andromeda-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-10-21T20:03:14+00:00", "hf_updated_at": null, "name": "Andromeda Alpha", "short_name": "Andromeda Alpha", "author": "openrouter", "description": "This model has been revealed as NVIDIA Nemotron Nano 2 VL. It continues to be offered for free by NVIDIA [here](https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free). \n\nThis is a small reasoning VLM trained for image understanding. It's strengths include multi-image comprehension (6+ images), especially those containing charts and text. This is a cloaked model provided to the community to gather feedback.\n\nNote: All prompts and output are logged to improve the provider’s model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "All prompts and output are logged to improve the provider’s model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.", "promotion_message": "", "routing_error_message": null, "permaslug": "openrouter/andromeda-alpha", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/sonoma-dusk-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-05T17:27:27.26817+00:00", "hf_updated_at": null, "name": "Sonoma Dusk Alpha", "short_name": "Sonoma Dusk Alpha", "author": "openrouter", "description": "This is a cloaked model provided to the community to gather feedback. A fast and intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling.\n\nNote: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "Sonoma Dusk Alpha were early test versions of [Grok 4 Fast](/x-ai/grok-4-fast:free), which is free to use for a limited time.”\n\nAll prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/sonoma-dusk-alpha", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/sonoma-sky-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-09-05T17:23:21.168091+00:00", "hf_updated_at": null, "name": "Sonoma Sky Alpha", "short_name": "Sonoma Sky Alpha", "author": "openrouter", "description": "This is a cloaked model provided to the community to gather feedback. A maximally intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling.\n\nNote: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "Sonoma Sky Alpha were early test versions of [Grok 4 Fast](/x-ai/grok-4-fast:free), which is free to use for a limited time.”\n\nAll prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/sonoma-sky-alpha", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-2.5-flash-image-preview", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-26T14:36:17+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Flash Image Preview (Nano Banana)", "short_name": "Gemini 2.5 Flash Image Preview (Nano Banana)", "author": "google", "description": "Gemini 2.5 Flash Image Preview, a.k.a. \"Nano Banana,\" is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "image", "text" ], "output_modalities": [ "image", "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-flash-image-preview", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "default_order": [ "google-vertex", "google-ai-studio" ], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/horizon-beta", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-08-01T23:03:39.887977+00:00", "hf_updated_at": null, "name": "Horizon Beta", "short_name": "Horizon Beta", "author": "openrouter", "description": "This is a cloaked model provided to the community to gather feedback. This is an improved version of [Horizon Alpha](/openrouter/horizon-alpha)\n\nNote: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "All prompts and completions for this model are logged by the provider and may be used to improve the model.", "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/horizon-beta", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/horizon-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-30T22:18:04+00:00", "hf_updated_at": null, "name": "Horizon Alpha", "short_name": "Horizon Alpha", "author": "openrouter", "description": "This was a cloaked model provided to the community to gather feedback. It has been deprecated - see [Horizon Beta](/openrouter/horizon-beta).\n\nNote: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.", "model_version_group_id": null, "context_length": 256000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "All prompts and completions for this model are logged by the provider and may be used to improve the model and other products and services. ", "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/horizon-alpha", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "thudm/glm-4.1v-9b-thinking", "hf_slug": "THUDM/GLM-4.1V-9B-Thinking", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-07-11T14:33:05.378045+00:00", "hf_updated_at": null, "name": "THUDM: GLM 4.1V 9B Thinking", "short_name": "GLM 4.1V 9B Thinking", "author": "thudm", "description": "GLM-4.1V-9B-Thinking is a 9B parameter vision-language model developed by THUDM, based on the GLM-4-9B foundation. It introduces a reasoning-centric \"thinking paradigm\" enhanced with reinforcement learning to improve multimodal reasoning, long-context understanding (up to 64K tokens), and complex problem solving. It achieves state-of-the-art performance among models in its class, outperforming even larger models like Qwen-2.5-VL-72B on a majority of benchmark tasks. ", "model_version_group_id": null, "context_length": 65536, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "thudm/glm-4.1v-9b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null }, "features": { "reasoning_config": { "start_token": "", "end_token": "", "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openai/codex-mini", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-05-16T15:36:01.081688+00:00", "hf_updated_at": null, "name": "OpenAI: Codex Mini", "short_name": "Codex Mini", "author": "openai", "description": "codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/codex-mini", "supports_reasoning": true, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "opengvlab/internvl3-14b", "hf_slug": "OpenGVLab/InternVL3-14B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-30T13:55:55.014183+00:00", "hf_updated_at": null, "name": "OpenGVLab: InternVL3 14B", "short_name": "InternVL3 14B", "author": "opengvlab", "description": "The 14b version of the InternVL3 series. An advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.", "model_version_group_id": null, "context_length": 32000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "opengvlab/internvl3-14b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "opengvlab/internvl3-2b", "hf_slug": "OpenGVLab/InternVL3-2B", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-30T13:30:07.912688+00:00", "hf_updated_at": null, "name": "OpenGVLab: InternVL3 2B", "short_name": "InternVL3 2B", "author": "opengvlab", "description": "The 2b version of the InternVL3 series, for an even higher inference speed and very reasonable performance. An advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.", "model_version_group_id": null, "context_length": 32000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "opengvlab/internvl3-2b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "moonshotai/kimi-vl-a3b-thinking", "hf_slug": "moonshotai/Kimi-VL-A3B-Thinking", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-10T17:07:21.175402+00:00", "hf_updated_at": null, "name": "MoonshotAI: Kimi VL A3B Thinking", "short_name": "Kimi VL A3B Thinking", "author": "moonshotai", "description": "Kimi-VL is a lightweight Mixture-of-Experts vision-language model that activates only 2.8B parameters per step while delivering strong performance on multimodal reasoning and long-context tasks. The Kimi-VL-A3B-Thinking variant, fine-tuned with chain-of-thought and reinforcement learning, excels in math and visual reasoning benchmarks like MathVision, MMMU, and MathVista, rivaling much larger models such as Qwen2.5-VL-7B and Gemma-3-12B. It supports 128K context and high-resolution input via its MoonViT encoder.", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "moonshotai/kimi-vl-a3b-thinking", "supports_reasoning": true, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/optimus-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-10T13:30:19+00:00", "hf_updated_at": null, "name": "Optimus Alpha", "short_name": "Optimus Alpha", "author": "openrouter", "description": "This is a cloaked model provided to the community to gather feedback. It's geared toward real world use cases, including programming.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/optimus-alpha", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openrouter/quasar-alpha", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-04-02T20:46:49.278785+00:00", "hf_updated_at": null, "name": "Quasar Alpha", "short_name": "Quasar Alpha", "author": "openrouter", "description": "This is a cloaked model provided to the community to gather feedback. It’s a powerful, all-purpose model supporting long-context tasks, including code generation.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openrouter/quasar-alpha", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "bytedance-research/ui-tars-72b", "hf_slug": "bytedance-research/UI-TARS-72B-DPO", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-26T20:14:25.673407+00:00", "hf_updated_at": null, "name": "Bytedance: UI-TARS 72B ", "short_name": "UI-TARS 72B ", "author": "bytedance-research", "description": "UI-TARS 72B is an open-source multimodal AI model designed specifically for automating browser and desktop tasks through visual interaction and control. The model is built with a specialized vision architecture enabling accurate interpretation and manipulation of on-screen visual data. It supports automation tasks within web browsers as well as desktop applications, including Microsoft Office and VS Code.\n\nCore capabilities include intelligent screen detection, predictive action modeling, and efficient handling of repetitive interactions. UI-TARS employs supervised fine-tuning (SFT) tailored explicitly for computer control scenarios. It can be deployed locally or accessed via Hugging Face for demonstration purposes. Intended use cases encompass workflow automation, task scripting, and interactive desktop control applications.", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "bytedance-research/ui-tars-72b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "qwen/qwen2.5-vl-3b-instruct", "hf_slug": "Qwen/Qwen2.5-VL-3B-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-26T18:42:53.41832+00:00", "hf_updated_at": null, "name": "Qwen: Qwen2.5 VL 3B Instruct", "short_name": "Qwen2.5 VL 3B Instruct", "author": "qwen", "description": "Qwen2.5 VL 3B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).", "model_version_group_id": null, "context_length": 64000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Qwen", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "qwen/qwen2.5-vl-3b-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-2.5-pro-exp-03-25", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-25T17:01:39.919989+00:00", "hf_updated_at": null, "name": "Google: Gemini 2.5 Pro Experimental", "short_name": "Gemini 2.5 Pro Experimental", "author": "google", "description": "This model has been deprecated by Google in favor of the (paid Preview model)[google/gemini-2.5-pro-preview]\n \nGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "model_version_group_id": null, "context_length": 1048576, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "This model has been deprecated by Google. Please switch to the [paid Gemini 2.5 Pro Preview endpoint](/google/gemini-2.5-pro-preview). ", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-2.5-pro-exp-03-25", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemma-3-1b-it", "hf_slug": "google/gemma-3-1b-it", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-14T14:45:56.842499+00:00", "hf_updated_at": null, "name": "Google: Gemma 3 1B", "short_name": "Gemma 3 1B", "author": "google", "description": "Gemma 3 1B is the smallest of the new Gemma 3 family. It handles context windows up to 32k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Note: Gemma 3 1B is not multimodal. For the smallest multimodal Gemma 3 model, please see [Gemma 3 4B](google/gemma-3-4b-it)", "model_version_group_id": "c99b277a-cfaf-4e93-9360-8a79cfa2b2c4", "context_length": 32000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": "gemma", "default_system": null, "default_stops": [ "", "", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemma-3-1b-it", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "microsoft/phi-4-multimodal-instruct", "hf_slug": "microsoft/Phi-4-multimodal-instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-03-08T01:11:24.652063+00:00", "hf_updated_at": null, "name": "Microsoft: Phi 4 Multimodal Instruct", "short_name": "Phi 4 Multimodal Instruct", "author": "microsoft", "description": "Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the [Phi-4 Multimodal blog post](https://azure.microsoft.com/en-us/blog/empowering-innovation-the-next-generation-of-the-phi-family/).\n", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Other", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "microsoft/phi-4-multimodal-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": null }, { "slug": "openai/gpt-4.5-preview", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2025-02-27T20:23:30.841555+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4.5 (Preview)", "short_name": "GPT-4.5 (Preview)", "author": "openai", "description": "GPT-4.5 (Preview) is a research preview of OpenAI’s latest language model, designed to advance capabilities in reasoning, creativity, and multi-turn conversation. It builds on previous iterations with improvements in world knowledge, contextual coherence, and the ability to follow user intent more effectively.\n\nThe model demonstrates enhanced performance in tasks that require open-ended thinking, problem-solving, and communication. Early testing suggests it is better at generating nuanced responses, maintaining long-context coherence, and reducing hallucinations compared to earlier versions.\n\nThis research preview is intended to help evaluate GPT-4.5’s strengths and limitations in real-world use cases as OpenAI continues to refine and develop future models. Read more at the [blog post here.](https://openai.com/index/introducing-gpt-4-5/)", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4.5-preview-2025-02-27", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "x-ai/grok-2-vision-1212", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-12-15T04:35:38.489105+00:00", "hf_updated_at": null, "name": "xAI: Grok 2 Vision 1212", "short_name": "Grok 2 Vision 1212", "author": "x-ai", "description": "Grok 2 Vision 1212 advances image-based AI with stronger visual comprehension, refined instruction-following, and multilingual support. From object recognition to style analysis, it empowers developers to build more intuitive, visually aware applications. Its enhanced steerability and reasoning establish a robust foundation for next-generation image solutions.\n\nTo read more about this model, check out [xAI's announcement](https://x.ai/blog/grok-1212).", "model_version_group_id": null, "context_length": 32768, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "x-ai/grok-2-vision-1212", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-exp-1121", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-21T19:18:45.23737+00:00", "hf_updated_at": null, "name": "Google: Gemini Experimental 1121", "short_name": "Gemini Experimental 1121", "author": "google", "description": "Experimental release (November 21st, 2024) of Gemini.", "model_version_group_id": null, "context_length": 40960, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-exp-1121", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "x-ai/grok-vision-beta", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-19T00:37:04.585936+00:00", "hf_updated_at": null, "name": "xAI: Grok Vision Beta", "short_name": "Grok Vision Beta", "author": "x-ai", "description": "Grok Vision Beta is xAI's experimental language model with vision capability.\n\n", "model_version_group_id": null, "context_length": 8192, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Grok", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "x-ai/grok-vision-beta", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-exp-1114", "hf_slug": "", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-15T23:52:20.203831+00:00", "hf_updated_at": null, "name": "Google: Gemini Experimental 1114", "short_name": "Gemini Experimental 1114", "author": "google", "description": "Gemini 11-14 (2024) experimental model features \"quality\" improvements.", "model_version_group_id": null, "context_length": 40960, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-exp-1114", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "anthropic/claude-3.5-haiku-20241022", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-11-04T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)", "short_name": "Claude 3.5 Haiku (2024-10-22)", "author": "anthropic", "description": "Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.\n\nIt does not support image inputs.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)", "model_version_group_id": "028ec497-a034-40fd-81fe-f51d0a0c640c", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-5-haiku-20241022", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-flash-1.5-8b", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-10-03T00:00:00+00:00", "hf_updated_at": null, "name": "Google: Gemini 1.5 Flash 8B", "short_name": "Gemini 1.5 Flash 8B", "author": "google", "description": "Gemini Flash 1.5 8B is optimized for speed and efficiency, offering enhanced performance in small prompt tasks like chat, transcription, and translation. With reduced latency, it is highly effective for real-time and large-scale operations. This model focuses on cost-effective solutions while maintaining high-quality results.\n\n[Click here to learn more about this model](https://developers.googleblog.com/en/gemini-15-flash-8b-is-now-generally-available-for-use/).\n\nUsage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms).", "model_version_group_id": "3a412ab9-b077-48de-884c-90843f7abbf2", "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-flash-1.5-8b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "meta-llama/llama-3.2-90b-vision-instruct", "hf_slug": "meta-llama/Llama-3.2-90B-Vision-Instruct", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-09-25T00:00:00+00:00", "hf_updated_at": null, "name": "Meta: Llama 3.2 90B Vision Instruct", "short_name": "Llama 3.2 90B Vision Instruct", "author": "meta-llama", "description": "The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image captioning, visual question answering, and advanced image-text comprehension. Pre-trained on vast multimodal datasets and fine-tuned with human feedback, the Llama 90B Vision is engineered to handle the most demanding image-based AI tasks.\n\nThis model is perfect for industries requiring cutting-edge multimodal AI capabilities, particularly those dealing with complex, real-time visual and textual analysis.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).", "model_version_group_id": null, "context_length": 131072, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama3", "instruct_type": "llama3", "default_system": null, "default_stops": [ "<|eot_id|>", "<|end_of_text|>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "meta-llama/llama-3.2-90b-vision-instruct", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": true, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-flash-1.5-exp", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-28T00:00:00+00:00", "hf_updated_at": null, "name": "Google: Gemini 1.5 Flash Experimental", "short_name": "Gemini 1.5 Flash Experimental", "author": "google", "description": "Gemini 1.5 Flash Experimental is an experimental version of the [Gemini 1.5 Flash](/models/google/gemini-flash-1.5) model.\n\nUsage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms).\n\n#multimodal\n\nNote: This model is experimental and not suited for production use-cases. It may be removed or redirected to another model in the future.", "model_version_group_id": "86ec374b-de4b-4920-a960-94f25078e303", "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-flash-1.5-exp", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "01-ai/yi-vision", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-02T00:00:00+00:00", "hf_updated_at": null, "name": "01.AI: Yi Vision", "short_name": "Yi Vision", "author": "01-ai", "description": "The Yi Vision is a complex visual task models provide high-performance understanding and analysis capabilities based on multiple images.\n\nIt's ideal for scenarios that require analysis and interpretation of images and charts, such as image question answering, chart understanding, OCR, visual reasoning, education, research report understanding, or multilingual document reading.", "model_version_group_id": null, "context_length": 16384, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Yi", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "01-ai/yi-vision", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-pro-1.5-exp", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-08-01T00:00:00+00:00", "hf_updated_at": null, "name": "Google: Gemini 1.5 Pro Experimental", "short_name": "Gemini 1.5 Pro Experimental", "author": "google", "description": "Gemini 1.5 Pro Experimental is a bleeding-edge version of the [Gemini 1.5 Pro](/models/google/gemini-pro-1.5) model. Because it's currently experimental, it will be **heavily rate-limited** by Google.\n\nUsage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms).\n\n#multimodal", "model_version_group_id": null, "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-pro-1.5-exp", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "anthropic/claude-3.5-sonnet-20240620", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-06-20T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3.5 Sonnet (2024-06-20)", "short_name": "Claude 3.5 Sonnet (2024-06-20)", "author": "anthropic", "description": "Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\nFor the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).\n\n#multimodal", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3.5-sonnet-20240620", "supports_reasoning": false, "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null }, "features": { "reasoning_config": { "start_token": null, "end_token": null, "system_prompt": null } }, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-flash-1.5", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-14T00:00:00+00:00", "hf_updated_at": null, "name": "Google: Gemini 1.5 Flash ", "short_name": "Gemini 1.5 Flash ", "author": "google", "description": "Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots.\n\nGemini 1.5 Flash is designed for high-volume, high-frequency tasks where cost and latency matter. On most common tasks, Flash achieves comparable quality to other Gemini Pro models at a significantly reduced cost. Flash is well-suited for applications like chat assistants and on-demand content generation where speed and scale matter.\n\nUsage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms).\n\n#multimodal", "model_version_group_id": "86ec374b-de4b-4920-a960-94f25078e303", "context_length": 1000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-flash-1.5", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "liuhaotian/llava-yi-34b", "hf_slug": "liuhaotian/llava-v1.6-34b", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-05-11T00:00:00+00:00", "hf_updated_at": null, "name": "LLaVA v1.6 34B", "short_name": "LLaVA v1.6 34B", "author": "liuhaotian", "description": "LLaVA Yi 34B is an open-source model trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: [NousResearch/Nous-Hermes-2-Yi-34B](/models/nousresearch/nous-hermes-yi-34b)\n\nIt was trained in December 2023.", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Yi", "instruct_type": "chatml", "default_system": null, "default_stops": [ "<|im_start|>", "<|im_end|>", "<|endoftext|>" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "liuhaotian/llava-yi-34b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "fireworks/firellava-13b", "hf_slug": "fireworks-ai/FireLLaVA-13b", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-04-26T00:00:00+00:00", "hf_updated_at": null, "name": "Fireworks: FireLLaVA 13B", "short_name": "FireLLaVA 13B", "author": "fireworks", "description": "A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4.\n\nThe first commercially permissive open source LLaVA model, trained entirely on open source LLM generated instruction following data.", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama2", "instruct_type": "vicuna", "default_system": null, "default_stops": [ "USER:", "" ], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "fireworks/firellava-13b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "google/gemini-pro-1.5", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-04-09T00:00:00+00:00", "hf_updated_at": null, "name": "Google: Gemini 1.5 Pro", "short_name": "Gemini 1.5 Pro", "author": "google", "description": "Google's latest multimodal model, supports image and video[0] in text or chat prompts.\n\nOptimized for language tasks including:\n\n- Code generation\n- Text generation\n- Text editing\n- Problem solving\n- Recommendations\n- Information extraction\n- Data extraction or generation\n- AI agents\n\nUsage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms).\n\n* [0]: Video input is not available through OpenRouter at this time.", "model_version_group_id": null, "context_length": 2000000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Gemini", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": "", "promotion_message": null, "routing_error_message": null, "permaslug": "google/gemini-pro-1.5", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "anthropic/claude-3-sonnet", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-03-05T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3 Sonnet", "short_name": "Claude 3 Sonnet", "author": "anthropic", "description": "Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)\n\n#multimodal", "model_version_group_id": "30636d20-cda3-4a59-aa0c-1a5b6efba072", "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-sonnet", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "anthropic/claude-3-opus", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2024-03-05T00:00:00+00:00", "hf_updated_at": null, "name": "Anthropic: Claude 3 Opus", "short_name": "Claude 3 Opus", "author": "anthropic", "description": "Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)\n\n#multimodal", "model_version_group_id": null, "context_length": 200000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Claude", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "anthropic/claude-3-opus", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "nousresearch/nous-hermes-2-vision-7b", "hf_slug": "NousResearch/Nous-Hermes-2-Vision-Alpha", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2023-12-07T00:00:00+00:00", "hf_updated_at": null, "name": "Nous: Hermes 2 Vision 7B (alpha)", "short_name": "Hermes 2 Vision 7B (alpha)", "author": "nousresearch", "description": "This vision-language model builds on innovations from the popular [OpenHermes-2.5](/models/teknium/openhermes-2.5-mistral-7b) model, by Teknium. It adds vision support, and is trained on a custom dataset enriched with function calling\n\nThis project is led by [qnguyen3](https://twitter.com/stablequan) and [teknium](https://twitter.com/Teknium1).\n\n#multimodal", "model_version_group_id": null, "context_length": 4096, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Mistral", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "nousresearch/nous-hermes-2-vision-7b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "liuhaotian/llava-13b", "hf_slug": "liuhaotian/llava-v1.6-vicuna-13b", "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2023-11-16T00:00:00+00:00", "hf_updated_at": null, "name": "LLaVA 13B", "short_name": "LLaVA 13B", "author": "liuhaotian", "description": "LLaVA is a large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities and setting a new state-of-the-art accuracy on Science QA.\n\n#multimodal", "model_version_group_id": null, "context_length": 2048, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "Llama2", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "liuhaotian/llava-13b", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null }, { "slug": "openai/gpt-4-vision-preview", "hf_slug": null, "updated_at": "2025-11-10T16:00:38.246665+00:00", "created_at": "2023-11-13T00:00:00+00:00", "hf_updated_at": null, "name": "OpenAI: GPT-4 Vision", "short_name": "GPT-4 Vision", "author": "openai", "description": "Ability to understand images, in addition to all other [GPT-4 Turbo capabilties](/models/openai/gpt-4-turbo). Training data: up to Apr 2023.\n\n**Note:** heavily rate limited by OpenAI while in preview.\n\n#multimodal", "model_version_group_id": null, "context_length": 128000, "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "has_text_output": true, "group": "GPT", "instruct_type": null, "default_system": null, "default_stops": [], "hidden": false, "router": null, "warning_message": null, "promotion_message": null, "routing_error_message": null, "permaslug": "openai/gpt-4-vision-preview", "supports_reasoning": false, "reasoning_config": null, "features": {}, "default_parameters": {}, "default_order": [], "quick_start_example_type": null, "is_trainable_text": null, "is_trainable_image": null, "endpoint": null } ], "analytics": { "baai/bge-large-en-v1.5-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "baai/bge-large-en-v1.5-20251117", "variant": "standard", "variant_permaslug": "baai/bge-large-en-v1.5-20251117", "count": 56000, "total_completion_tokens": 0, "total_prompt_tokens": 301743491, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4.7-20251222": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.7-20251222", "variant": "standard", "variant_permaslug": "z-ai/glm-4.7-20251222", "count": 7326994, "total_completion_tokens": 7166727805, "total_prompt_tokens": 124679568471, "total_native_tokens_reasoning": 3472150501, "num_media_prompt": 3960, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 66105749567, "total_tool_calls": 3844651, "requests_with_tool_call_errors": 106939 }, "openai/gpt-4o-audio-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-audio-preview", "variant": "standard", "variant_permaslug": "openai/gpt-4o-audio-preview", "count": 27582, "total_completion_tokens": 4801902, "total_prompt_tokens": 12966368, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 26322, "total_native_tokens_cached": 0, "total_tool_calls": 181, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-r1-distill-qwen-32b": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-r1-distill-qwen-32b", "variant": "standard", "variant_permaslug": "deepseek/deepseek-r1-distill-qwen-32b", "count": 315466, "total_completion_tokens": 123379010, "total_prompt_tokens": 262042012, "total_native_tokens_reasoning": 125713604, "num_media_prompt": 26, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthropic/claude-4.5-haiku-20251001": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4.5-haiku-20251001", "variant": "standard", "variant_permaslug": "anthropic/claude-4.5-haiku-20251001", "count": 10568707, "total_completion_tokens": 4894010141, "total_prompt_tokens": 95650710853, "total_native_tokens_reasoning": 351130316, "num_media_prompt": 605539, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 39504635529, "total_tool_calls": 3583893, "requests_with_tool_call_errors": 93524 }, "thenlper/gte-base-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "thenlper/gte-base-20251117", "variant": "standard", "variant_permaslug": "thenlper/gte-base-20251117", "count": 268509, "total_completion_tokens": 0, "total_prompt_tokens": 517139623, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-embedding-001": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-embedding-001", "variant": "standard", "variant_permaslug": "google/gemini-embedding-001", "count": 3125195, "total_completion_tokens": 0, "total_prompt_tokens": 11491693627, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "tencent/hunyuan-a13b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "tencent/hunyuan-a13b-instruct", "variant": "standard", "variant_permaslug": "tencent/hunyuan-a13b-instruct", "count": 17731, "total_completion_tokens": 3593634, "total_prompt_tokens": 23816463, "total_native_tokens_reasoning": 45339, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/ministral-8b-2512": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/ministral-8b-2512", "variant": "standard", "variant_permaslug": "mistralai/ministral-8b-2512", "count": 682571, "total_completion_tokens": 94416421, "total_prompt_tokens": 766270291, "total_native_tokens_reasoning": 0, "num_media_prompt": 13776, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 8805, "requests_with_tool_call_errors": 286 }, "deepseek/deepseek-chat-v3": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-chat-v3", "variant": "standard", "variant_permaslug": "deepseek/deepseek-chat-v3", "count": 5933001, "total_completion_tokens": 1027859492, "total_prompt_tokens": 9444356305, "total_native_tokens_reasoning": 0, "num_media_prompt": 192, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 491471211, "total_tool_calls": 163068, "requests_with_tool_call_errors": 2485 }, "perplexity/sonar-pro": { "date": "2026-01-19 00:00:00", "model_permaslug": "perplexity/sonar-pro", "variant": "standard", "variant_permaslug": "perplexity/sonar-pro", "count": 313682, "total_completion_tokens": 141896142, "total_prompt_tokens": 628573035, "total_native_tokens_reasoning": 0, "num_media_prompt": 1739, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nvidia/nemotron-nano-9b-v2": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-nano-9b-v2", "variant": "standard", "variant_permaslug": "nvidia/nemotron-nano-9b-v2", "count": 234059, "total_completion_tokens": 237424934, "total_prompt_tokens": 1851261229, "total_native_tokens_reasoning": 146735698, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 9503, "requests_with_tool_call_errors": 64 }, "bytedance-seed/seedream-4.5-20251203": { "date": "2026-01-19 00:00:00", "model_permaslug": "bytedance-seed/seedream-4.5-20251203", "variant": "standard", "variant_permaslug": "bytedance-seed/seedream-4.5-20251203", "count": 144847, "total_completion_tokens": 604736225, "total_prompt_tokens": 359909974, "total_native_tokens_reasoning": 0, "num_media_prompt": 200249, "num_media_completion": 144847, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-2.0-flash-lite-001": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.0-flash-lite-001", "variant": "standard", "variant_permaslug": "google/gemini-2.0-flash-lite-001", "count": 22917372, "total_completion_tokens": 4336482928, "total_prompt_tokens": 31347706424, "total_native_tokens_reasoning": 0, "num_media_prompt": 4095938, "num_media_completion": 0, "num_audio_prompt": 8060, "total_native_tokens_cached": 0, "total_tool_calls": 994113, "requests_with_tool_call_errors": 50641 }, "tngtech/tng-r1t-chimera": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/tng-r1t-chimera", "variant": "standard", "variant_permaslug": "tngtech/tng-r1t-chimera", "count": 6734, "total_completion_tokens": 4003602, "total_prompt_tokens": 28843712, "total_native_tokens_reasoning": 2828318, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5687040, "total_tool_calls": 14, "requests_with_tool_call_errors": 0 }, "minimax/minimax-01": { "date": "2026-01-19 00:00:00", "model_permaslug": "minimax/minimax-01", "variant": "standard", "variant_permaslug": "minimax/minimax-01", "count": 426369, "total_completion_tokens": 45176314, "total_prompt_tokens": 995697421, "total_native_tokens_reasoning": 0, "num_media_prompt": 1538, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-2.5-pro": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-pro", "variant": "standard", "variant_permaslug": "google/gemini-2.5-pro", "count": 10780156, "total_completion_tokens": 18953499128, "total_prompt_tokens": 122564258747, "total_native_tokens_reasoning": 10863268000, "num_media_prompt": 1617577, "num_media_completion": 0, "num_audio_prompt": 42784, "total_native_tokens_cached": 41631826713, "total_tool_calls": 449386, "requests_with_tool_call_errors": 16005 }, "mistralai/devstral-medium-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/devstral-medium-2507", "variant": "standard", "variant_permaslug": "mistralai/devstral-medium-2507", "count": 10817, "total_completion_tokens": 1161667, "total_prompt_tokens": 58111545, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1099, "requests_with_tool_call_errors": 175 }, "meta-llama/llama-3-8b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3-8b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3-8b-instruct", "count": 10071240, "total_completion_tokens": 209321216, "total_prompt_tokens": 5640372687, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 230, "requests_with_tool_call_errors": 49 }, "qwen/qwen3-next-80b-a3b-thinking-2509": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-next-80b-a3b-thinking-2509", "variant": "standard", "variant_permaslug": "qwen/qwen3-next-80b-a3b-thinking-2509", "count": 298687, "total_completion_tokens": 1377894120, "total_prompt_tokens": 872215138, "total_native_tokens_reasoning": 1220871412, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2269434, "total_tool_calls": 11836, "requests_with_tool_call_errors": 205 }, "openai/gpt-oss-120b:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-120b", "variant": "free", "variant_permaslug": "openai/gpt-oss-120b:free", "count": 297335, "total_completion_tokens": 219162308, "total_prompt_tokens": 2552257624, "total_native_tokens_reasoning": 135565268, "num_media_prompt": 2, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 48563, "requests_with_tool_call_errors": 9997 }, "minimax/minimax-m1": { "date": "2026-01-19 00:00:00", "model_permaslug": "minimax/minimax-m1", "variant": "standard", "variant_permaslug": "minimax/minimax-m1", "count": 7817, "total_completion_tokens": 7106799, "total_prompt_tokens": 139459466, "total_native_tokens_reasoning": 4700939, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1516, "requests_with_tool_call_errors": 110 }, "prime-intellect/intellect-3-20251126": { "date": "2026-01-19 00:00:00", "model_permaslug": "prime-intellect/intellect-3-20251126", "variant": "standard", "variant_permaslug": "prime-intellect/intellect-3-20251126", "count": 12187, "total_completion_tokens": 28105469, "total_prompt_tokens": 27679118, "total_native_tokens_reasoning": 16803717, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 4392032, "total_tool_calls": 697, "requests_with_tool_call_errors": 3 }, "qwen/qwen3-30b-a3b-thinking-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-30b-a3b-thinking-2507", "variant": "standard", "variant_permaslug": "qwen/qwen3-30b-a3b-thinking-2507", "count": 152838, "total_completion_tokens": 220747983, "total_prompt_tokens": 815517449, "total_native_tokens_reasoning": 207872997, "num_media_prompt": 6, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 16807, "requests_with_tool_call_errors": 4428 }, "amazon/nova-pro-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "amazon/nova-pro-v1", "variant": "standard", "variant_permaslug": "amazon/nova-pro-v1", "count": 32946, "total_completion_tokens": 4291169, "total_prompt_tokens": 31785345, "total_native_tokens_reasoning": 0, "num_media_prompt": 8986, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 174, "requests_with_tool_call_errors": 12 }, "anthropic/claude-3-7-sonnet-20250219:thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-3-7-sonnet-20250219", "variant": "thinking", "variant_permaslug": "anthropic/claude-3-7-sonnet-20250219:thinking", "count": 124765, "total_completion_tokens": 197876448, "total_prompt_tokens": 2247362567, "total_native_tokens_reasoning": 107544503, "num_media_prompt": 19249, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 845269929, "total_tool_calls": 31038, "requests_with_tool_call_errors": 1135 }, "qwen/qwen-plus-2025-01-25": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-plus-2025-01-25", "variant": "standard", "variant_permaslug": "qwen/qwen-plus-2025-01-25", "count": 33043, "total_completion_tokens": 9475756, "total_prompt_tokens": 93280663, "total_native_tokens_reasoning": 16527, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 7807593, "total_tool_calls": 630, "requests_with_tool_call_errors": 98 }, "bytedance/ui-tars-1.5-7b": { "date": "2026-01-19 00:00:00", "model_permaslug": "bytedance/ui-tars-1.5-7b", "variant": "standard", "variant_permaslug": "bytedance/ui-tars-1.5-7b", "count": 51511, "total_completion_tokens": 2232961, "total_prompt_tokens": 125770709, "total_native_tokens_reasoning": 0, "num_media_prompt": 136687, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 38059216, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "meta-llama/llama-4-maverick-17b-128e-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-4-maverick-17b-128e-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-4-maverick-17b-128e-instruct", "count": 10143224, "total_completion_tokens": 1032604550, "total_prompt_tokens": 20252517533, "total_native_tokens_reasoning": 0, "num_media_prompt": 1598470, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 756278012, "total_tool_calls": 229109, "requests_with_tool_call_errors": 4230 }, "deepcogito/cogito-v2-preview-llama-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepcogito/cogito-v2-preview-llama-70b", "variant": "standard", "variant_permaslug": "deepcogito/cogito-v2-preview-llama-70b", "count": 3870, "total_completion_tokens": 548889, "total_prompt_tokens": 4287286, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 28, "requests_with_tool_call_errors": 0 }, "google/gemma-2-9b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-2-9b-it", "variant": "standard", "variant_permaslug": "google/gemma-2-9b-it", "count": 1694384, "total_completion_tokens": 502347769, "total_prompt_tokens": 1202088087, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "relace/relace-apply-3": { "date": "2026-01-19 00:00:00", "model_permaslug": "relace/relace-apply-3", "variant": "standard", "variant_permaslug": "relace/relace-apply-3", "count": 21942, "total_completion_tokens": 43565758, "total_prompt_tokens": 65298540, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-embed-2312": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-embed-2312", "variant": "standard", "variant_permaslug": "mistralai/mistral-embed-2312", "count": 115832, "total_completion_tokens": 0, "total_prompt_tokens": 164760373, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-large-2407": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-large-2407", "variant": "standard", "variant_permaslug": "mistralai/mistral-large-2407", "count": 8885, "total_completion_tokens": 3880628, "total_prompt_tokens": 23365163, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 773, "requests_with_tool_call_errors": 50 }, "openai/gpt-oss-safeguard-20b": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-safeguard-20b", "variant": "standard", "variant_permaslug": "openai/gpt-oss-safeguard-20b", "count": 1740019, "total_completion_tokens": 916063158, "total_prompt_tokens": 4979040258, "total_native_tokens_reasoning": 684413109, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3801686784, "total_tool_calls": 51543, "requests_with_tool_call_errors": 374 }, "mistralai/devstral-2512:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/devstral-2512", "variant": "free", "variant_permaslug": "mistralai/devstral-2512:free", "count": 10594999, "total_completion_tokens": 4598306315, "total_prompt_tokens": 146943045358, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2724884, "requests_with_tool_call_errors": 165205 }, "mistralai/pixtral-large-2411": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/pixtral-large-2411", "variant": "standard", "variant_permaslug": "mistralai/pixtral-large-2411", "count": 17079, "total_completion_tokens": 3658461, "total_prompt_tokens": 47146237, "total_native_tokens_reasoning": 0, "num_media_prompt": 13665, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 425, "requests_with_tool_call_errors": 72 }, "openai/o4-mini-high-2025-04-16": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o4-mini-high-2025-04-16", "variant": "standard", "variant_permaslug": "openai/o4-mini-high-2025-04-16", "count": 91184, "total_completion_tokens": 122735450, "total_prompt_tokens": 376252306, "total_native_tokens_reasoning": 102812504, "num_media_prompt": 8373, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 139692928, "total_tool_calls": 4915, "requests_with_tool_call_errors": 0 }, "openai/gpt-4o-mini-2024-07-18": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-mini-2024-07-18", "variant": "standard", "variant_permaslug": "openai/gpt-4o-mini-2024-07-18", "count": 3162539, "total_completion_tokens": 421374822, "total_prompt_tokens": 7606086792, "total_native_tokens_reasoning": 0, "num_media_prompt": 12664, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3048499200, "total_tool_calls": 108896, "requests_with_tool_call_errors": 127 }, "allenai/olmo-3-7b-think-20251121": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/olmo-3-7b-think-20251121", "variant": "standard", "variant_permaslug": "allenai/olmo-3-7b-think-20251121", "count": 27677, "total_completion_tokens": 58928656, "total_prompt_tokens": 18987653, "total_native_tokens_reasoning": 70320406, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3380192, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4.5v": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.5v", "variant": "standard", "variant_permaslug": "z-ai/glm-4.5v", "count": 31164, "total_completion_tokens": 16135432, "total_prompt_tokens": 73146472, "total_native_tokens_reasoning": 8783618, "num_media_prompt": 118474, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 10110739, "total_tool_calls": 1124, "requests_with_tool_call_errors": 189 }, "gryphe/mythomax-l2-13b": { "date": "2026-01-19 00:00:00", "model_permaslug": "gryphe/mythomax-l2-13b", "variant": "standard", "variant_permaslug": "gryphe/mythomax-l2-13b", "count": 1506570, "total_completion_tokens": 219510857, "total_prompt_tokens": 1553012977, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-3-pro-preview-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-3-pro-preview-20251117", "variant": "standard", "variant_permaslug": "google/gemini-3-pro-preview-20251117", "count": 9892425, "total_completion_tokens": 21414757024, "total_prompt_tokens": 146558026906, "total_native_tokens_reasoning": 14414102833, "num_media_prompt": 4162447, "num_media_completion": 0, "num_audio_prompt": 511519, "total_native_tokens_cached": 80549468622, "total_tool_calls": 1375732, "requests_with_tool_call_errors": 32236 }, "perplexity/sonar": { "date": "2026-01-19 00:00:00", "model_permaslug": "perplexity/sonar", "variant": "standard", "variant_permaslug": "perplexity/sonar", "count": 798796, "total_completion_tokens": 299240117, "total_prompt_tokens": 664100180, "total_native_tokens_reasoning": 0, "num_media_prompt": 6773, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-r1-0528": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-r1-0528", "variant": "standard", "variant_permaslug": "deepseek/deepseek-r1-0528", "count": 1544153, "total_completion_tokens": 2215709216, "total_prompt_tokens": 12164290190, "total_native_tokens_reasoning": 1558355699, "num_media_prompt": 2447, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2515918238, "total_tool_calls": 52994, "requests_with_tool_call_errors": 761 }, "xiaomi/mimo-v2-flash-20251210": { "date": "2026-01-19 00:00:00", "model_permaslug": "xiaomi/mimo-v2-flash-20251210", "variant": "standard", "variant_permaslug": "xiaomi/mimo-v2-flash-20251210", "count": 1943166, "total_completion_tokens": 740454249, "total_prompt_tokens": 11455424408, "total_native_tokens_reasoning": 143206691, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 6032144183, "total_tool_calls": 181852, "requests_with_tool_call_errors": 7767 }, "qwen/qwen3-next-80b-a3b-instruct-2509": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-next-80b-a3b-instruct-2509", "variant": "standard", "variant_permaslug": "qwen/qwen3-next-80b-a3b-instruct-2509", "count": 2876915, "total_completion_tokens": 673532132, "total_prompt_tokens": 17875297548, "total_native_tokens_reasoning": 0, "num_media_prompt": 168, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1217351630, "total_tool_calls": 194121, "requests_with_tool_call_errors": 15257 }, "qwen/qwen-plus-2025-07-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-plus-2025-07-28", "variant": "standard", "variant_permaslug": "qwen/qwen-plus-2025-07-28", "count": 22195, "total_completion_tokens": 13045146, "total_prompt_tokens": 170367803, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 8889, "requests_with_tool_call_errors": 398 }, "meta-llama/llama-3.1-70b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.1-70b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.1-70b-instruct", "count": 4364390, "total_completion_tokens": 418065223, "total_prompt_tokens": 4559441228, "total_native_tokens_reasoning": 0, "num_media_prompt": 4, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 10253, "requests_with_tool_call_errors": 772 }, "meta-llama/llama-3-70b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3-70b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3-70b-instruct", "count": 1599367, "total_completion_tokens": 49533185, "total_prompt_tokens": 1053324356, "total_native_tokens_reasoning": 0, "num_media_prompt": 3, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-7b-instruct-v0.3": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-7b-instruct-v0.3", "variant": "standard", "variant_permaslug": "mistralai/mistral-7b-instruct-v0.3", "count": 383910, "total_completion_tokens": 18806873, "total_prompt_tokens": 124936558, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen-turbo-2024-11-01": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-turbo-2024-11-01", "variant": "standard", "variant_permaslug": "qwen/qwen-turbo-2024-11-01", "count": 910687, "total_completion_tokens": 195574768, "total_prompt_tokens": 2076465032, "total_native_tokens_reasoning": 16492, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 237985366, "total_tool_calls": 25415, "requests_with_tool_call_errors": 273 }, "meituan/longcat-flash-chat": { "date": "2026-01-19 00:00:00", "model_permaslug": "meituan/longcat-flash-chat", "variant": "standard", "variant_permaslug": "meituan/longcat-flash-chat", "count": 220789, "total_completion_tokens": 50544891, "total_prompt_tokens": 1092736265, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 577060608, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "switchpoint/router": { "date": "2026-01-19 00:00:00", "model_permaslug": "switchpoint/router", "variant": "standard", "variant_permaslug": "switchpoint/router", "count": 2416, "total_completion_tokens": 1274731, "total_prompt_tokens": 4573203, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4.5-air": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.5-air", "variant": "standard", "variant_permaslug": "z-ai/glm-4.5-air", "count": 2316148, "total_completion_tokens": 566681876, "total_prompt_tokens": 8523603457, "total_native_tokens_reasoning": 254236178, "num_media_prompt": 1, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5103777316, "total_tool_calls": 151412, "requests_with_tool_call_errors": 13067 }, "google/gemini-2.5-flash-image": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-flash-image", "variant": "standard", "variant_permaslug": "google/gemini-2.5-flash-image", "count": 1458384, "total_completion_tokens": 1371494036, "total_prompt_tokens": 1512274934, "total_native_tokens_reasoning": 10891, "num_media_prompt": 1368784, "num_media_completion": 1023950, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4.6-20251208": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.6-20251208", "variant": "standard", "variant_permaslug": "z-ai/glm-4.6-20251208", "count": 250922, "total_completion_tokens": 758698311, "total_prompt_tokens": 2234777448, "total_native_tokens_reasoning": 565917377, "num_media_prompt": 223729, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 345750388, "total_tool_calls": 42018, "requests_with_tool_call_errors": 2397 }, "openai/gpt-5-nano-2025-08-07": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-nano-2025-08-07", "variant": "standard", "variant_permaslug": "openai/gpt-5-nano-2025-08-07", "count": 8533756, "total_completion_tokens": 9637117127, "total_prompt_tokens": 28156498975, "total_native_tokens_reasoning": 8546398027, "num_media_prompt": 563845, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5781763200, "total_tool_calls": 1779796, "requests_with_tool_call_errors": 4144 }, "perplexity/sonar-pro-search": { "date": "2026-01-19 00:00:00", "model_permaslug": "perplexity/sonar-pro-search", "variant": "standard", "variant_permaslug": "perplexity/sonar-pro-search", "count": 80370, "total_completion_tokens": 39446810, "total_prompt_tokens": 135073279, "total_native_tokens_reasoning": 0, "num_media_prompt": 1339, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1706, "requests_with_tool_call_errors": 0 }, "neversleep/noromaid-20b": { "date": "2026-01-19 00:00:00", "model_permaslug": "neversleep/noromaid-20b", "variant": "standard", "variant_permaslug": "neversleep/noromaid-20b", "count": 16906, "total_completion_tokens": 2357472, "total_prompt_tokens": 25556092, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemma-3-27b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-27b-it", "variant": "standard", "variant_permaslug": "google/gemma-3-27b-it", "count": 13041622, "total_completion_tokens": 2041183774, "total_prompt_tokens": 20217477100, "total_native_tokens_reasoning": 0, "num_media_prompt": 2806874, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2003308696, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-chat-v3.1": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-chat-v3.1", "variant": "standard", "variant_permaslug": "deepseek/deepseek-chat-v3.1", "count": 26139768, "total_completion_tokens": 4343426603, "total_prompt_tokens": 95339386393, "total_native_tokens_reasoning": 702763319, "num_media_prompt": 385, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 10730007416, "total_tool_calls": 228597, "requests_with_tool_call_errors": 6087 }, "deepseek/deepseek-v3.2-20251201": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-v3.2-20251201", "variant": "standard", "variant_permaslug": "deepseek/deepseek-v3.2-20251201", "count": 53257850, "total_completion_tokens": 23649787150, "total_prompt_tokens": 416145678347, "total_native_tokens_reasoning": 5367372095, "num_media_prompt": 5308, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 174575670000, "total_tool_calls": 1700424, "requests_with_tool_call_errors": 41664 }, "qwen/qwen3-32b-04-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-32b-04-28", "variant": "standard", "variant_permaslug": "qwen/qwen3-32b-04-28", "count": 11727702, "total_completion_tokens": 2547491846, "total_prompt_tokens": 12551192732, "total_native_tokens_reasoning": 1809460224, "num_media_prompt": 3, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2461644792, "total_tool_calls": 260352, "requests_with_tool_call_errors": 7057 }, "mistralai/ministral-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/ministral-8b", "variant": "standard", "variant_permaslug": "mistralai/ministral-8b", "count": 1361613, "total_completion_tokens": 371260724, "total_prompt_tokens": 581306189, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 13760, "requests_with_tool_call_errors": 307 }, "mistralai/mistral-saba-2502": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-saba-2502", "variant": "standard", "variant_permaslug": "mistralai/mistral-saba-2502", "count": 29670, "total_completion_tokens": 638776, "total_prompt_tokens": 4152071, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 20, "requests_with_tool_call_errors": 0 }, "openai/o3-2025-04-16": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o3-2025-04-16", "variant": "standard", "variant_permaslug": "openai/o3-2025-04-16", "count": 148689, "total_completion_tokens": 135006853, "total_prompt_tokens": 762496785, "total_native_tokens_reasoning": 83438014, "num_media_prompt": 78466, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 341476096, "total_tool_calls": 15237, "requests_with_tool_call_errors": 1 }, "qwen/qwen3-coder-480b-a35b-07-25:exacto": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-480b-a35b-07-25", "variant": "exacto", "variant_permaslug": "qwen/qwen3-coder-480b-a35b-07-25:exacto", "count": 30683, "total_completion_tokens": 8788690, "total_prompt_tokens": 1445637919, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 918901615, "total_tool_calls": 21596, "requests_with_tool_call_errors": 661 }, "raifle/sorcererlm-8x22b": { "date": "2026-01-19 00:00:00", "model_permaslug": "raifle/sorcererlm-8x22b", "variant": "standard", "variant_permaslug": "raifle/sorcererlm-8x22b", "count": 2899, "total_completion_tokens": 898820, "total_prompt_tokens": 7968231, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5.1-codex-20251113": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.1-codex-20251113", "variant": "standard", "variant_permaslug": "openai/gpt-5.1-codex-20251113", "count": 121428, "total_completion_tokens": 71681309, "total_prompt_tokens": 3793123607, "total_native_tokens_reasoning": 43627205, "num_media_prompt": 19149, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3163285504, "total_tool_calls": 57820, "requests_with_tool_call_errors": 444 }, "deepcogito/cogito-v2-preview-llama-405b": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepcogito/cogito-v2-preview-llama-405b", "variant": "standard", "variant_permaslug": "deepcogito/cogito-v2-preview-llama-405b", "count": 2896, "total_completion_tokens": 567975, "total_prompt_tokens": 5169281, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 321, "requests_with_tool_call_errors": 5 }, "amazon/nova-lite-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "amazon/nova-lite-v1", "variant": "standard", "variant_permaslug": "amazon/nova-lite-v1", "count": 380831, "total_completion_tokens": 7336424, "total_prompt_tokens": 248864490, "total_native_tokens_reasoning": 0, "num_media_prompt": 323472, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1157, "requests_with_tool_call_errors": 21 }, "ai21/jamba-mini-1.7": { "date": "2026-01-19 00:00:00", "model_permaslug": "ai21/jamba-mini-1.7", "variant": "standard", "variant_permaslug": "ai21/jamba-mini-1.7", "count": 6254, "total_completion_tokens": 1827673, "total_prompt_tokens": 14898287, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 264, "requests_with_tool_call_errors": 117 }, "nvidia/llama-3.1-nemotron-ultra-253b-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/llama-3.1-nemotron-ultra-253b-v1", "variant": "standard", "variant_permaslug": "nvidia/llama-3.1-nemotron-ultra-253b-v1", "count": 4442794, "total_completion_tokens": 39267636, "total_prompt_tokens": 2880404878, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "moonshotai/kimi-dev-72b": { "date": "2026-01-19 00:00:00", "model_permaslug": "moonshotai/kimi-dev-72b", "variant": "standard", "variant_permaslug": "moonshotai/kimi-dev-72b", "count": 2682, "total_completion_tokens": 5278023, "total_prompt_tokens": 5963342, "total_native_tokens_reasoning": 3441842, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepcogito/cogito-v2.1-671b-20251118": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepcogito/cogito-v2.1-671b-20251118", "variant": "standard", "variant_permaslug": "deepcogito/cogito-v2.1-671b-20251118", "count": 35018, "total_completion_tokens": 4644141, "total_prompt_tokens": 99001779, "total_native_tokens_reasoning": 1003632, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "allenai/olmo-3.1-32b-instruct-20251215": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/olmo-3.1-32b-instruct-20251215", "variant": "standard", "variant_permaslug": "allenai/olmo-3.1-32b-instruct-20251215", "count": 75062, "total_completion_tokens": 56402666, "total_prompt_tokens": 156057705, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 113, "requests_with_tool_call_errors": 7 }, "mistralai/codestral-embed-2505": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/codestral-embed-2505", "variant": "standard", "variant_permaslug": "mistralai/codestral-embed-2505", "count": 139439, "total_completion_tokens": 0, "total_prompt_tokens": 483559519, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5-codex": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-codex", "variant": "standard", "variant_permaslug": "openai/gpt-5-codex", "count": 41915, "total_completion_tokens": 44116692, "total_prompt_tokens": 1753290451, "total_native_tokens_reasoning": 32906737, "num_media_prompt": 9662, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1444822784, "total_tool_calls": 23684, "requests_with_tool_call_errors": 229 }, "qwen/qwen3-coder-flash": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-flash", "variant": "standard", "variant_permaslug": "qwen/qwen3-coder-flash", "count": 29226, "total_completion_tokens": 9814216, "total_prompt_tokens": 184805618, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 4868, "requests_with_tool_call_errors": 340 }, "mistralai/ministral-14b-2512": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/ministral-14b-2512", "variant": "standard", "variant_permaslug": "mistralai/ministral-14b-2512", "count": 962263, "total_completion_tokens": 118344319, "total_prompt_tokens": 1920892986, "total_native_tokens_reasoning": 0, "num_media_prompt": 61496, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 50716, "requests_with_tool_call_errors": 691 }, "openai/gpt-3.5-turbo-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-3.5-turbo-instruct", "variant": "standard", "variant_permaslug": "openai/gpt-3.5-turbo-instruct", "count": 35555, "total_completion_tokens": 5557395, "total_prompt_tokens": 15509656, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "cohere/command-r-plus-08-2024": { "date": "2026-01-19 00:00:00", "model_permaslug": "cohere/command-r-plus-08-2024", "variant": "standard", "variant_permaslug": "cohere/command-r-plus-08-2024", "count": 17400, "total_completion_tokens": 3685981, "total_prompt_tokens": 30974067, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2003, "requests_with_tool_call_errors": 242 }, "baidu/ernie-4.5-300b-a47b": { "date": "2026-01-19 00:00:00", "model_permaslug": "baidu/ernie-4.5-300b-a47b", "variant": "standard", "variant_permaslug": "baidu/ernie-4.5-300b-a47b", "count": 109163, "total_completion_tokens": 27477499, "total_prompt_tokens": 205335482, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 13336128, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/text-embedding-3-small": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/text-embedding-3-small", "variant": "standard", "variant_permaslug": "openai/text-embedding-3-small", "count": 17518036, "total_completion_tokens": 0, "total_prompt_tokens": 29941259162, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/o3-deep-research-2025-06-26": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o3-deep-research-2025-06-26", "variant": "standard", "variant_permaslug": "openai/o3-deep-research-2025-06-26", "count": 3777, "total_completion_tokens": 37509753, "total_prompt_tokens": 62160506, "total_native_tokens_reasoning": 31903648, "num_media_prompt": 309, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1920000, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "baidu/ernie-4.5-vl-424b-a47b": { "date": "2026-01-19 00:00:00", "model_permaslug": "baidu/ernie-4.5-vl-424b-a47b", "variant": "standard", "variant_permaslug": "baidu/ernie-4.5-vl-424b-a47b", "count": 5888, "total_completion_tokens": 3564971, "total_prompt_tokens": 21391641, "total_native_tokens_reasoning": 381414, "num_media_prompt": 873, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "black-forest-labs/flux.2-klein-4b": { "date": "2026-01-19 00:00:00", "model_permaslug": "black-forest-labs/flux.2-klein-4b", "variant": "standard", "variant_permaslug": "black-forest-labs/flux.2-klein-4b", "count": 27218, "total_completion_tokens": 0, "total_prompt_tokens": 6058023, "total_native_tokens_reasoning": 0, "num_media_prompt": 8371, "num_media_completion": 27218, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sentence-transformers/all-minilm-l12-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "sentence-transformers/all-minilm-l12-v2-20251117", "variant": "standard", "variant_permaslug": "sentence-transformers/all-minilm-l12-v2-20251117", "count": 9467527, "total_completion_tokens": 0, "total_prompt_tokens": 1237609904, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nvidia/nemotron-3-nano-30b-a3b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-3-nano-30b-a3b", "variant": "standard", "variant_permaslug": "nvidia/nemotron-3-nano-30b-a3b", "count": 577192, "total_completion_tokens": 2241294227, "total_prompt_tokens": 1840432830, "total_native_tokens_reasoning": 2159825592, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 23473, "requests_with_tool_call_errors": 7385 }, "thenlper/gte-large-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "thenlper/gte-large-20251117", "variant": "standard", "variant_permaslug": "thenlper/gte-large-20251117", "count": 61854, "total_completion_tokens": 0, "total_prompt_tokens": 58099045, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nvidia/nemotron-3-nano-30b-a3b:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-3-nano-30b-a3b", "variant": "free", "variant_permaslug": "nvidia/nemotron-3-nano-30b-a3b:free", "count": 465379, "total_completion_tokens": 1023767338, "total_prompt_tokens": 3230621601, "total_native_tokens_reasoning": 794532679, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 54361, "requests_with_tool_call_errors": 13555 }, "qwen/qwq-32b": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwq-32b", "variant": "standard", "variant_permaslug": "qwen/qwq-32b", "count": 106911, "total_completion_tokens": 152561647, "total_prompt_tokens": 211161725, "total_native_tokens_reasoning": 140650447, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 100, "requests_with_tool_call_errors": 9 }, "x-ai/grok-code-fast-1": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-code-fast-1", "variant": "standard", "variant_permaslug": "x-ai/grok-code-fast-1", "count": 15899673, "total_completion_tokens": 26696679793, "total_prompt_tokens": 567580333280, "total_native_tokens_reasoning": 19832616079, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 434330497856, "total_tool_calls": 5451422, "requests_with_tool_call_errors": 15042 }, "meta-llama/llama-guard-3-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-guard-3-8b", "variant": "standard", "variant_permaslug": "meta-llama/llama-guard-3-8b", "count": 60527, "total_completion_tokens": 110777100, "total_prompt_tokens": 13096421, "total_native_tokens_reasoning": 0, "num_media_prompt": 1, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "baidu/ernie-4.5-21b-a3b": { "date": "2026-01-19 00:00:00", "model_permaslug": "baidu/ernie-4.5-21b-a3b", "variant": "standard", "variant_permaslug": "baidu/ernie-4.5-21b-a3b", "count": 182894, "total_completion_tokens": 11371707, "total_prompt_tokens": 94912075, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sentence-transformers/all-mpnet-base-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "sentence-transformers/all-mpnet-base-v2-20251117", "variant": "standard", "variant_permaslug": "sentence-transformers/all-mpnet-base-v2-20251117", "count": 2058, "total_completion_tokens": 0, "total_prompt_tokens": 2718315, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-coder-480b-a35b-07-25": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-480b-a35b-07-25", "variant": "standard", "variant_permaslug": "qwen/qwen3-coder-480b-a35b-07-25", "count": 6335868, "total_completion_tokens": 2228665815, "total_prompt_tokens": 107754969823, "total_native_tokens_reasoning": 0, "num_media_prompt": 241, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 12119976176, "total_tool_calls": 367692, "requests_with_tool_call_errors": 59710 }, "openai/gpt-5-pro-2025-10-06": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-pro-2025-10-06", "variant": "standard", "variant_permaslug": "openai/gpt-5-pro-2025-10-06", "count": 6193, "total_completion_tokens": 15668074, "total_prompt_tokens": 37522362, "total_native_tokens_reasoning": 12954829, "num_media_prompt": 1220, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 246, "requests_with_tool_call_errors": 0 }, "openai/gpt-4o-search-preview-2025-03-11": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-search-preview-2025-03-11", "variant": "standard", "variant_permaslug": "openai/gpt-4o-search-preview-2025-03-11", "count": 47133, "total_completion_tokens": 17262691, "total_prompt_tokens": 31468892, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-30b-a3b-04-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-30b-a3b-04-28", "variant": "standard", "variant_permaslug": "qwen/qwen3-30b-a3b-04-28", "count": 1401176, "total_completion_tokens": 994521415, "total_prompt_tokens": 3193991037, "total_native_tokens_reasoning": 987782488, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 110250995, "total_tool_calls": 16598, "requests_with_tool_call_errors": 10709 }, "thedrummer/unslopnemo-12b": { "date": "2026-01-19 00:00:00", "model_permaslug": "thedrummer/unslopnemo-12b", "variant": "standard", "variant_permaslug": "thedrummer/unslopnemo-12b", "count": 450702, "total_completion_tokens": 75652110, "total_prompt_tokens": 1408710952, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "x-ai/grok-4.1-fast": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-4.1-fast", "variant": "standard", "variant_permaslug": "x-ai/grok-4.1-fast", "count": 47427569, "total_completion_tokens": 38002522893, "total_prompt_tokens": 271402744172, "total_native_tokens_reasoning": 27479133279, "num_media_prompt": 8396324, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 88719842273, "total_tool_calls": 4813231, "requests_with_tool_call_errors": 52286 }, "openai/gpt-4o-2024-05-13": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-2024-05-13", "variant": "standard", "variant_permaslug": "openai/gpt-4o-2024-05-13", "count": 39639, "total_completion_tokens": 11613112, "total_prompt_tokens": 39084844, "total_native_tokens_reasoning": 0, "num_media_prompt": 849, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 731008, "total_tool_calls": 5314, "requests_with_tool_call_errors": 251 }, "nousresearch/hermes-2-pro-llama-3-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-2-pro-llama-3-8b", "variant": "standard", "variant_permaslug": "nousresearch/hermes-2-pro-llama-3-8b", "count": 97934, "total_completion_tokens": 5888875, "total_prompt_tokens": 59774444, "total_native_tokens_reasoning": 0, "num_media_prompt": 1, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/voxtral-small-24b-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/voxtral-small-24b-2507", "variant": "standard", "variant_permaslug": "mistralai/voxtral-small-24b-2507", "count": 75705, "total_completion_tokens": 4766524, "total_prompt_tokens": 33785457, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 10673, "total_native_tokens_cached": 0, "total_tool_calls": 628, "requests_with_tool_call_errors": 1 }, "google/gemma-3-27b-it:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-27b-it", "variant": "free", "variant_permaslug": "google/gemma-3-27b-it:free", "count": 726513, "total_completion_tokens": 569119463, "total_prompt_tokens": 3308238335, "total_native_tokens_reasoning": 0, "num_media_prompt": 91438, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1334, "requests_with_tool_call_errors": 126 }, "ai21/jamba-large-1.7": { "date": "2026-01-19 00:00:00", "model_permaslug": "ai21/jamba-large-1.7", "variant": "standard", "variant_permaslug": "ai21/jamba-large-1.7", "count": 10327, "total_completion_tokens": 4614615, "total_prompt_tokens": 34193371, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 28, "requests_with_tool_call_errors": 7 }, "inflection/inflection-3-productivity": { "date": "2026-01-19 00:00:00", "model_permaslug": "inflection/inflection-3-productivity", "variant": "standard", "variant_permaslug": "inflection/inflection-3-productivity", "count": 2514, "total_completion_tokens": 519207, "total_prompt_tokens": 1525486, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "meta-llama/llama-guard-4-12b": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-guard-4-12b", "variant": "standard", "variant_permaslug": "meta-llama/llama-guard-4-12b", "count": 3002198, "total_completion_tokens": 11260246, "total_prompt_tokens": 1239841940, "total_native_tokens_reasoning": 0, "num_media_prompt": 1794, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/o1-pro": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o1-pro", "variant": "standard", "variant_permaslug": "openai/o1-pro", "count": 1317, "total_completion_tokens": 1115072, "total_prompt_tokens": 2128699, "total_native_tokens_reasoning": 727296, "num_media_prompt": 181, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-4b-04-28:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-4b-04-28", "variant": "free", "variant_permaslug": "qwen/qwen3-4b-04-28:free", "count": 30271, "total_completion_tokens": 38967228, "total_prompt_tokens": 48283796, "total_native_tokens_reasoning": 33277948, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 455, "requests_with_tool_call_errors": 308 }, "neversleep/llama-3.1-lumimaid-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "neversleep/llama-3.1-lumimaid-8b", "variant": "standard", "variant_permaslug": "neversleep/llama-3.1-lumimaid-8b", "count": 47779, "total_completion_tokens": 6420163, "total_prompt_tokens": 100259159, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "minimax/minimax-m2-her-20260123": { "date": "2026-01-24 00:00:00", "model_permaslug": "minimax/minimax-m2-her-20260123", "variant": "standard", "variant_permaslug": "minimax/minimax-m2-her-20260123", "count": 40722, "total_completion_tokens": 11868646, "total_prompt_tokens": 120384653, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4o:extended": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o", "variant": "extended", "variant_permaslug": "openai/gpt-4o:extended", "count": 2052, "total_completion_tokens": 818727, "total_prompt_tokens": 14652854, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 100, "requests_with_tool_call_errors": 21 }, "qwen/qwen-vl-plus": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-vl-plus", "variant": "standard", "variant_permaslug": "qwen/qwen-vl-plus", "count": 41749, "total_completion_tokens": 3907581, "total_prompt_tokens": 66157285, "total_native_tokens_reasoning": 0, "num_media_prompt": 35807, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "amazon/nova-premier-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "amazon/nova-premier-v1", "variant": "standard", "variant_permaslug": "amazon/nova-premier-v1", "count": 11532, "total_completion_tokens": 1430151, "total_prompt_tokens": 30905804, "total_native_tokens_reasoning": 0, "num_media_prompt": 11744, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 293, "requests_with_tool_call_errors": 21 }, "x-ai/grok-3-mini": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-3-mini", "variant": "standard", "variant_permaslug": "x-ai/grok-3-mini", "count": 3810063, "total_completion_tokens": 3035518513, "total_prompt_tokens": 7221862269, "total_native_tokens_reasoning": 2458013955, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2064734279, "total_tool_calls": 64796, "requests_with_tool_call_errors": 21484 }, "openai/gpt-audio": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-audio", "variant": "standard", "variant_permaslug": "openai/gpt-audio", "count": 1005, "total_completion_tokens": 536578, "total_prompt_tokens": 1395530, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 1011, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4.1-2025-04-14": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4.1-2025-04-14", "variant": "standard", "variant_permaslug": "openai/gpt-4.1-2025-04-14", "count": 7844751, "total_completion_tokens": 1306013515, "total_prompt_tokens": 31722949437, "total_native_tokens_reasoning": 0, "num_media_prompt": 534024, "num_media_completion": 2, "num_audio_prompt": 0, "total_native_tokens_cached": 14270786560, "total_tool_calls": 752355, "requests_with_tool_call_errors": 5668 }, "inception/mercury": { "date": "2026-01-19 00:00:00", "model_permaslug": "inception/mercury", "variant": "standard", "variant_permaslug": "inception/mercury", "count": 24524, "total_completion_tokens": 5079353, "total_prompt_tokens": 24509510, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 143, "requests_with_tool_call_errors": 20 }, "nvidia/llama-3.1-nemotron-70b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/llama-3.1-nemotron-70b-instruct", "variant": "standard", "variant_permaslug": "nvidia/llama-3.1-nemotron-70b-instruct", "count": 19588, "total_completion_tokens": 7099164, "total_prompt_tokens": 51722141, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 507, "requests_with_tool_call_errors": 228 }, "qwen/qwen3-vl-30b-a3b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-30b-a3b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-30b-a3b-instruct", "count": 1531426, "total_completion_tokens": 259572632, "total_prompt_tokens": 4500935545, "total_native_tokens_reasoning": 81, "num_media_prompt": 2125835, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 693451868, "total_tool_calls": 70104, "requests_with_tool_call_errors": 1227 }, "baidu/ernie-4.5-vl-28b-a3b": { "date": "2026-01-19 00:00:00", "model_permaslug": "baidu/ernie-4.5-vl-28b-a3b", "variant": "standard", "variant_permaslug": "baidu/ernie-4.5-vl-28b-a3b", "count": 3540, "total_completion_tokens": 1793889, "total_prompt_tokens": 3050807, "total_native_tokens_reasoning": 39313, "num_media_prompt": 2055, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "microsoft/wizardlm-2-8x22b": { "date": "2026-01-19 00:00:00", "model_permaslug": "microsoft/wizardlm-2-8x22b", "variant": "standard", "variant_permaslug": "microsoft/wizardlm-2-8x22b", "count": 578837, "total_completion_tokens": 112454946, "total_prompt_tokens": 1147142220, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-v3.2-speciale-20251201": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-v3.2-speciale-20251201", "variant": "standard", "variant_permaslug": "deepseek/deepseek-v3.2-speciale-20251201", "count": 180829, "total_completion_tokens": 930417214, "total_prompt_tokens": 890055823, "total_native_tokens_reasoning": 864858200, "num_media_prompt": 127, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 242214592, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "alfredpros/codellama-7b-instruct-solidity": { "date": "2026-01-19 00:00:00", "model_permaslug": "alfredpros/codellama-7b-instruct-solidity", "variant": "standard", "variant_permaslug": "alfredpros/codellama-7b-instruct-solidity", "count": 9786, "total_completion_tokens": 4178045, "total_prompt_tokens": 1819048, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "essentialai/rnj-1-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "essentialai/rnj-1-instruct", "variant": "standard", "variant_permaslug": "essentialai/rnj-1-instruct", "count": 11787, "total_completion_tokens": 1520226, "total_prompt_tokens": 12267248, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-oss-20b": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-20b", "variant": "standard", "variant_permaslug": "openai/gpt-oss-20b", "count": 19312303, "total_completion_tokens": 12715219060, "total_prompt_tokens": 42136401057, "total_native_tokens_reasoning": 10020222255, "num_media_prompt": 209, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 12706507541, "total_tool_calls": 383362, "requests_with_tool_call_errors": 76770 }, "minimax/minimax-m2.1": { "date": "2026-01-19 00:00:00", "model_permaslug": "minimax/minimax-m2.1", "variant": "standard", "variant_permaslug": "minimax/minimax-m2.1", "count": 3526547, "total_completion_tokens": 2435110684, "total_prompt_tokens": 116402426791, "total_native_tokens_reasoning": 1116173114, "num_media_prompt": 434, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 89048390158, "total_tool_calls": 2029625, "requests_with_tool_call_errors": 69110 }, "openai/gpt-4o-mini": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-mini", "variant": "standard", "variant_permaslug": "openai/gpt-4o-mini", "count": 60680673, "total_completion_tokens": 6360988566, "total_prompt_tokens": 138793367698, "total_native_tokens_reasoning": 0, "num_media_prompt": 1357134, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 34998984576, "total_tool_calls": 3056398, "requests_with_tool_call_errors": 110056 }, "openai/gpt-4o-2024-11-20": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-2024-11-20", "variant": "standard", "variant_permaslug": "openai/gpt-4o-2024-11-20", "count": 612052, "total_completion_tokens": 102512202, "total_prompt_tokens": 999436113, "total_native_tokens_reasoning": 0, "num_media_prompt": 100897, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 206370176, "total_tool_calls": 15821, "requests_with_tool_call_errors": 377 }, "morph/morph-v3-large": { "date": "2026-01-19 00:00:00", "model_permaslug": "morph/morph-v3-large", "variant": "standard", "variant_permaslug": "morph/morph-v3-large", "count": 102228, "total_completion_tokens": 432132667, "total_prompt_tokens": 489091349, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "moonshotai/kimi-k2-thinking-20251106": { "date": "2026-01-19 00:00:00", "model_permaslug": "moonshotai/kimi-k2-thinking-20251106", "variant": "standard", "variant_permaslug": "moonshotai/kimi-k2-thinking-20251106", "count": 1396962, "total_completion_tokens": 2116423704, "total_prompt_tokens": 20993230600, "total_native_tokens_reasoning": 1653928358, "num_media_prompt": 3519, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 11084168483, "total_tool_calls": 482265, "requests_with_tool_call_errors": 9383 }, "nousresearch/deephermes-3-mistral-24b-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/deephermes-3-mistral-24b-preview", "variant": "standard", "variant_permaslug": "nousresearch/deephermes-3-mistral-24b-preview", "count": 4473, "total_completion_tokens": 942124, "total_prompt_tokens": 12119545, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2636638, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "meta-llama/llama-4-scout-17b-16e-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-4-scout-17b-16e-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-4-scout-17b-16e-instruct", "count": 4002437, "total_completion_tokens": 473428859, "total_prompt_tokens": 7644298987, "total_native_tokens_reasoning": 0, "num_media_prompt": 2095725, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 8233, "requests_with_tool_call_errors": 117 }, "mistralai/mistral-nemo": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-nemo", "variant": "standard", "variant_permaslug": "mistralai/mistral-nemo", "count": 25092923, "total_completion_tokens": 3172232567, "total_prompt_tokens": 73938925717, "total_native_tokens_reasoning": 0, "num_media_prompt": 1205, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3532856591, "total_tool_calls": 25369, "requests_with_tool_call_errors": 121 }, "arcee-ai/trinity-mini-20251201:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "arcee-ai/trinity-mini-20251201", "variant": "free", "variant_permaslug": "arcee-ai/trinity-mini-20251201:free", "count": 108476, "total_completion_tokens": 163583893, "total_prompt_tokens": 480310583, "total_native_tokens_reasoning": 124197785, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 4354, "requests_with_tool_call_errors": 1385 }, "google/gemini-2.5-flash-preview-09-2025": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-flash-preview-09-2025", "variant": "standard", "variant_permaslug": "google/gemini-2.5-flash-preview-09-2025", "count": 982226, "total_completion_tokens": 491908325, "total_prompt_tokens": 10463861887, "total_native_tokens_reasoning": 113833818, "num_media_prompt": 102932, "num_media_completion": 0, "num_audio_prompt": 375, "total_native_tokens_cached": 4625613140, "total_tool_calls": 99897, "requests_with_tool_call_errors": 3203 }, "qwen/qwen3-coder-480b-a35b-07-25:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-480b-a35b-07-25", "variant": "free", "variant_permaslug": "qwen/qwen3-coder-480b-a35b-07-25:free", "count": 149972, "total_completion_tokens": 88429107, "total_prompt_tokens": 4081024124, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 43797, "requests_with_tool_call_errors": 1491 }, "inflection/inflection-3-pi": { "date": "2026-01-19 00:00:00", "model_permaslug": "inflection/inflection-3-pi", "variant": "standard", "variant_permaslug": "inflection/inflection-3-pi", "count": 22821, "total_completion_tokens": 555932, "total_prompt_tokens": 2391856, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "thedrummer/rocinante-12b": { "date": "2026-01-19 00:00:00", "model_permaslug": "thedrummer/rocinante-12b", "variant": "standard", "variant_permaslug": "thedrummer/rocinante-12b", "count": 485782, "total_completion_tokens": 135881553, "total_prompt_tokens": 825514993, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "intfloat/multilingual-e5-large-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "intfloat/multilingual-e5-large-20251117", "variant": "standard", "variant_permaslug": "intfloat/multilingual-e5-large-20251117", "count": 1223709, "total_completion_tokens": 0, "total_prompt_tokens": 351916702, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "morph/morph-v3-fast": { "date": "2026-01-19 00:00:00", "model_permaslug": "morph/morph-v3-fast", "variant": "standard", "variant_permaslug": "morph/morph-v3-fast", "count": 9863, "total_completion_tokens": 47105360, "total_prompt_tokens": 47515524, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "liquid/lfm-2.5-1.2b-thinking-20260120:free": { "date": "2026-01-20 00:00:00", "model_permaslug": "liquid/lfm-2.5-1.2b-thinking-20260120", "variant": "free", "variant_permaslug": "liquid/lfm-2.5-1.2b-thinking-20260120:free", "count": 60889, "total_completion_tokens": 74178052, "total_prompt_tokens": 157185295, "total_native_tokens_reasoning": 67559769, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "tngtech/deepseek-r1t2-chimera": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/deepseek-r1t2-chimera", "variant": "standard", "variant_permaslug": "tngtech/deepseek-r1t2-chimera", "count": 914190, "total_completion_tokens": 436390509, "total_prompt_tokens": 4558361985, "total_native_tokens_reasoning": 648503925, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 513858944, "total_tool_calls": 241, "requests_with_tool_call_errors": 5 }, "deepseek/deepseek-v3.1-terminus": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-v3.1-terminus", "variant": "standard", "variant_permaslug": "deepseek/deepseek-v3.1-terminus", "count": 2407143, "total_completion_tokens": 1226306945, "total_prompt_tokens": 12330540601, "total_native_tokens_reasoning": 456697957, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 875479848, "total_tool_calls": 95994, "requests_with_tool_call_errors": 3228 }, "x-ai/grok-3": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-3", "variant": "standard", "variant_permaslug": "x-ai/grok-3", "count": 410928, "total_completion_tokens": 145880736, "total_prompt_tokens": 1430128861, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 283069230, "total_tool_calls": 6474, "requests_with_tool_call_errors": 23 }, "amazon/nova-micro-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "amazon/nova-micro-v1", "variant": "standard", "variant_permaslug": "amazon/nova-micro-v1", "count": 1631001, "total_completion_tokens": 406537118, "total_prompt_tokens": 4269168968, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 378, "requests_with_tool_call_errors": 46 }, "perplexity/sonar-deep-research": { "date": "2026-01-19 00:00:00", "model_permaslug": "perplexity/sonar-deep-research", "variant": "standard", "variant_permaslug": "perplexity/sonar-deep-research", "count": 13917, "total_completion_tokens": 3419854140, "total_prompt_tokens": 52769030, "total_native_tokens_reasoning": 3336125169, "num_media_prompt": 55, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-2.5-flash": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-flash", "variant": "standard", "variant_permaslug": "google/gemini-2.5-flash", "count": 115785936, "total_completion_tokens": 32611605879, "total_prompt_tokens": 373321024571, "total_native_tokens_reasoning": 4462350310, "num_media_prompt": 23460483, "num_media_completion": 0, "num_audio_prompt": 228520, "total_native_tokens_cached": 95919357244, "total_tool_calls": 10388484, "requests_with_tool_call_errors": 197257 }, "allenai/olmo-3-7b-instruct-20251121": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/olmo-3-7b-instruct-20251121", "variant": "standard", "variant_permaslug": "allenai/olmo-3-7b-instruct-20251121", "count": 31889, "total_completion_tokens": 4109996, "total_prompt_tokens": 34795445, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5825520, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "meta-llama/llama-3.2-1b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.2-1b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.2-1b-instruct", "count": 75992, "total_completion_tokens": 48745808, "total_prompt_tokens": 32523389, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sao10k/l3.1-70b-hanami-x1": { "date": "2026-01-19 00:00:00", "model_permaslug": "sao10k/l3.1-70b-hanami-x1", "variant": "standard", "variant_permaslug": "sao10k/l3.1-70b-hanami-x1", "count": 3046, "total_completion_tokens": 781790, "total_prompt_tokens": 3683174, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemma-3n-e4b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3n-e4b-it", "variant": "standard", "variant_permaslug": "google/gemma-3n-e4b-it", "count": 1548728, "total_completion_tokens": 96473759, "total_prompt_tokens": 418274605, "total_native_tokens_reasoning": 0, "num_media_prompt": 11, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-coder-plus": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-plus", "variant": "standard", "variant_permaslug": "qwen/qwen3-coder-plus", "count": 41916, "total_completion_tokens": 14190066, "total_prompt_tokens": 523823636, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 12076, "requests_with_tool_call_errors": 571 }, "inception/mercury-coder-small-beta": { "date": "2026-01-19 00:00:00", "model_permaslug": "inception/mercury-coder-small-beta", "variant": "standard", "variant_permaslug": "inception/mercury-coder-small-beta", "count": 12809, "total_completion_tokens": 18097310, "total_prompt_tokens": 44407937, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 341, "requests_with_tool_call_errors": 83 }, "opengvlab/internvl3-78b": { "date": "2026-01-19 00:00:00", "model_permaslug": "opengvlab/internvl3-78b", "variant": "standard", "variant_permaslug": "opengvlab/internvl3-78b", "count": 439907, "total_completion_tokens": 11242917, "total_prompt_tokens": 237294717, "total_native_tokens_reasoning": 0, "num_media_prompt": 43777, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 90987104, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthropic/claude-4-sonnet-20250522": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4-sonnet-20250522", "variant": "standard", "variant_permaslug": "anthropic/claude-4-sonnet-20250522", "count": 4473746, "total_completion_tokens": 2981170223, "total_prompt_tokens": 48009673174, "total_native_tokens_reasoning": 49199513, "num_media_prompt": 383372, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 22743990787, "total_tool_calls": 725864, "requests_with_tool_call_errors": 17083 }, "meta-llama/llama-3.1-8b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.1-8b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.1-8b-instruct", "count": 32859297, "total_completion_tokens": 2367797022, "total_prompt_tokens": 26505562786, "total_native_tokens_reasoning": 0, "num_media_prompt": 48, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 6979016576, "total_tool_calls": 738993, "requests_with_tool_call_errors": 7838 }, "cohere/command-a-03-2025": { "date": "2026-01-19 00:00:00", "model_permaslug": "cohere/command-a-03-2025", "variant": "standard", "variant_permaslug": "cohere/command-a-03-2025", "count": 9318, "total_completion_tokens": 2341154, "total_prompt_tokens": 13450745, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-3.5-turbo-0613": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-3.5-turbo-0613", "variant": "standard", "variant_permaslug": "openai/gpt-3.5-turbo-0613", "count": 71223, "total_completion_tokens": 17493137, "total_prompt_tokens": 20673462, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 229248, "total_tool_calls": 62, "requests_with_tool_call_errors": 0 }, "google/gemini-2.0-flash-exp:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.0-flash-exp", "variant": "free", "variant_permaslug": "google/gemini-2.0-flash-exp:free", "count": 182702, "total_completion_tokens": 78877919, "total_prompt_tokens": 1294295802, "total_native_tokens_reasoning": 1, "num_media_prompt": 64243, "num_media_completion": 541, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 6257, "requests_with_tool_call_errors": 605 }, "qwen/qwen2.5-vl-72b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen2.5-vl-72b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen2.5-vl-72b-instruct", "count": 1106859, "total_completion_tokens": 139119314, "total_prompt_tokens": 2674424670, "total_native_tokens_reasoning": 0, "num_media_prompt": 1311297, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 207595840, "total_tool_calls": 90, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-small-3.1-24b-instruct-2503:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "variant": "free", "variant_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503:free", "count": 45848, "total_completion_tokens": 21706501, "total_prompt_tokens": 149500868, "total_native_tokens_reasoning": 0, "num_media_prompt": 787, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 205, "requests_with_tool_call_errors": 205 }, "mistralai/mistral-medium-3": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-medium-3", "variant": "standard", "variant_permaslug": "mistralai/mistral-medium-3", "count": 68864, "total_completion_tokens": 53579248, "total_prompt_tokens": 722558562, "total_native_tokens_reasoning": 0, "num_media_prompt": 925, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 501, "requests_with_tool_call_errors": 23 }, "openai/gpt-4-turbo": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4-turbo", "variant": "standard", "variant_permaslug": "openai/gpt-4-turbo", "count": 62782, "total_completion_tokens": 15096715, "total_prompt_tokens": 148424003, "total_native_tokens_reasoning": 0, "num_media_prompt": 24741, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 3647, "requests_with_tool_call_errors": 204 }, "qwen/qwen3-vl-32b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-32b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-32b-instruct", "count": 146066, "total_completion_tokens": 114466340, "total_prompt_tokens": 354130396, "total_native_tokens_reasoning": 0, "num_media_prompt": 166599, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-v3.2-exp": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-v3.2-exp", "variant": "standard", "variant_permaslug": "deepseek/deepseek-v3.2-exp", "count": 3610632, "total_completion_tokens": 1640237768, "total_prompt_tokens": 19119441936, "total_native_tokens_reasoning": 496727268, "num_media_prompt": 2422, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 740679616, "total_tool_calls": 537819, "requests_with_tool_call_errors": 7073 }, "openai/gpt-5.2-pro-20251211": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.2-pro-20251211", "variant": "standard", "variant_permaslug": "openai/gpt-5.2-pro-20251211", "count": 111026, "total_completion_tokens": 212193122, "total_prompt_tokens": 2062310256, "total_native_tokens_reasoning": 144353142, "num_media_prompt": 51709, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 13346, "requests_with_tool_call_errors": 234 }, "z-ai/glm-4.5": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.5", "variant": "standard", "variant_permaslug": "z-ai/glm-4.5", "count": 483671, "total_completion_tokens": 494396061, "total_prompt_tokens": 4495392820, "total_native_tokens_reasoning": 382434383, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3261340260, "total_tool_calls": 186815, "requests_with_tool_call_errors": 56210 }, "minimax/minimax-m2": { "date": "2026-01-19 00:00:00", "model_permaslug": "minimax/minimax-m2", "variant": "standard", "variant_permaslug": "minimax/minimax-m2", "count": 569359, "total_completion_tokens": 288164974, "total_prompt_tokens": 13223292344, "total_native_tokens_reasoning": 204961516, "num_media_prompt": 320, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5209906073, "total_tool_calls": 299239, "requests_with_tool_call_errors": 17438 }, "thedrummer/cydonia-24b-v4.1": { "date": "2026-01-19 00:00:00", "model_permaslug": "thedrummer/cydonia-24b-v4.1", "variant": "standard", "variant_permaslug": "thedrummer/cydonia-24b-v4.1", "count": 178970, "total_completion_tokens": 48528779, "total_prompt_tokens": 974524827, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 637825792, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-tiny": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-tiny", "variant": "standard", "variant_permaslug": "mistralai/mistral-tiny", "count": 3166286, "total_completion_tokens": 44993440, "total_prompt_tokens": 1478147544, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-embedding-4b": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-embedding-4b", "variant": "standard", "variant_permaslug": "qwen/qwen3-embedding-4b", "count": 3065377, "total_completion_tokens": 0, "total_prompt_tokens": 1333957295, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-small-creative-20251216": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-small-creative-20251216", "variant": "standard", "variant_permaslug": "mistralai/mistral-small-creative-20251216", "count": 771570, "total_completion_tokens": 321148319, "total_prompt_tokens": 3750591514, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 14750, "requests_with_tool_call_errors": 1151 }, "openai/gpt-oss-120b": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-120b", "variant": "standard", "variant_permaslug": "openai/gpt-oss-120b", "count": 61918702, "total_completion_tokens": 32739021051, "total_prompt_tokens": 243369618486, "total_native_tokens_reasoning": 13933748855, "num_media_prompt": 2192, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 41773390730, "total_tool_calls": 978567, "requests_with_tool_call_errors": 93678 }, "openai/gpt-5-image": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-image", "variant": "standard", "variant_permaslug": "openai/gpt-5-image", "count": 14952, "total_completion_tokens": 63900324, "total_prompt_tokens": 51058716, "total_native_tokens_reasoning": 20173151, "num_media_prompt": 16762, "num_media_completion": 8705, "num_audio_prompt": 0, "total_native_tokens_cached": 4415744, "total_tool_calls": 92, "requests_with_tool_call_errors": 1 }, "anthropic/claude-4.1-opus-20250805": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4.1-opus-20250805", "variant": "standard", "variant_permaslug": "anthropic/claude-4.1-opus-20250805", "count": 104379, "total_completion_tokens": 59742156, "total_prompt_tokens": 1226252147, "total_native_tokens_reasoning": 7069461, "num_media_prompt": 11178, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 327534743, "total_tool_calls": 10941, "requests_with_tool_call_errors": 165 }, "z-ai/glm-4.5-air:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.5-air", "variant": "free", "variant_permaslug": "z-ai/glm-4.5-air:free", "count": 1773597, "total_completion_tokens": 1511322639, "total_prompt_tokens": 21983748101, "total_native_tokens_reasoning": 763641378, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 11929038042, "total_tool_calls": 256023, "requests_with_tool_call_errors": 22197 }, "google/gemini-3-flash-preview-20251217": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-3-flash-preview-20251217", "variant": "standard", "variant_permaslug": "google/gemini-3-flash-preview-20251217", "count": 74003236, "total_completion_tokens": 33872964299, "total_prompt_tokens": 557730950089, "total_native_tokens_reasoning": 7798049552, "num_media_prompt": 18896703, "num_media_completion": 0, "num_audio_prompt": 419881, "total_native_tokens_cached": 231981520427, "total_tool_calls": 14944012, "requests_with_tool_call_errors": 254550 }, "undi95/remm-slerp-l2-13b": { "date": "2026-01-19 00:00:00", "model_permaslug": "undi95/remm-slerp-l2-13b", "variant": "standard", "variant_permaslug": "undi95/remm-slerp-l2-13b", "count": 182287, "total_completion_tokens": 18421400, "total_prompt_tokens": 272887760, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "relace/relace-search-20251208": { "date": "2026-01-19 00:00:00", "model_permaslug": "relace/relace-search-20251208", "variant": "standard", "variant_permaslug": "relace/relace-search-20251208", "count": 24404, "total_completion_tokens": 1409292, "total_prompt_tokens": 14521163, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 376, "requests_with_tool_call_errors": 10 }, "openai/gpt-5-image-mini": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-image-mini", "variant": "standard", "variant_permaslug": "openai/gpt-5-image-mini", "count": 54241, "total_completion_tokens": 125008706, "total_prompt_tokens": 112078812, "total_native_tokens_reasoning": 46416933, "num_media_prompt": 39835, "num_media_completion": 14279, "num_audio_prompt": 0, "total_native_tokens_cached": 6076544, "total_tool_calls": 59, "requests_with_tool_call_errors": 3 }, "deepseek/deepseek-v3.1-terminus:exacto": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-v3.1-terminus", "variant": "exacto", "variant_permaslug": "deepseek/deepseek-v3.1-terminus:exacto", "count": 276181, "total_completion_tokens": 140441832, "total_prompt_tokens": 2646441579, "total_native_tokens_reasoning": 22626243, "num_media_prompt": 26, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 89932428, "total_tool_calls": 36181, "requests_with_tool_call_errors": 1571 }, "openai/gpt-5.2-20251211": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.2-20251211", "variant": "standard", "variant_permaslug": "openai/gpt-5.2-20251211", "count": 7661946, "total_completion_tokens": 7080958767, "total_prompt_tokens": 96972656070, "total_native_tokens_reasoning": 4026126811, "num_media_prompt": 1321717, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 54688884864, "total_tool_calls": 2093266, "requests_with_tool_call_errors": 10048 }, "writer/palmyra-x5-20250428": { "date": "2026-01-21 00:00:00", "model_permaslug": "writer/palmyra-x5-20250428", "variant": "standard", "variant_permaslug": "writer/palmyra-x5-20250428", "count": 22260, "total_completion_tokens": 13458218, "total_prompt_tokens": 214539884, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4-32b-0414": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4-32b-0414", "variant": "standard", "variant_permaslug": "z-ai/glm-4-32b-0414", "count": 16399297, "total_completion_tokens": 125023141, "total_prompt_tokens": 5542380209, "total_native_tokens_reasoning": 0, "num_media_prompt": 49, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 9904, "requests_with_tool_call_errors": 18 }, "sourceful/riverflow-v2-max-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "sourceful/riverflow-v2-max-preview", "variant": "standard", "variant_permaslug": "sourceful/riverflow-v2-max-preview", "count": 2805, "total_completion_tokens": 11710875, "total_prompt_tokens": 8019702, "total_native_tokens_reasoning": 0, "num_media_prompt": 3141, "num_media_completion": 2805, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/devstral-2512": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/devstral-2512", "variant": "standard", "variant_permaslug": "mistralai/devstral-2512", "count": 341621, "total_completion_tokens": 102754367, "total_prompt_tokens": 3451339635, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2705307824, "total_tool_calls": 14494, "requests_with_tool_call_errors": 383 }, "anthropic/claude-3-haiku": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-3-haiku", "variant": "standard", "variant_permaslug": "anthropic/claude-3-haiku", "count": 1830991, "total_completion_tokens": 378758962, "total_prompt_tokens": 2429285955, "total_native_tokens_reasoning": 0, "num_media_prompt": 41423, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 112997293, "total_tool_calls": 137916, "requests_with_tool_call_errors": 3247 }, "nvidia/nemotron-nano-12b-v2-vl:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-nano-12b-v2-vl", "variant": "free", "variant_permaslug": "nvidia/nemotron-nano-12b-v2-vl:free", "count": 89427, "total_completion_tokens": 109140367, "total_prompt_tokens": 352717588, "total_native_tokens_reasoning": 81088126, "num_media_prompt": 49683, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1198, "requests_with_tool_call_errors": 569 }, "bytedance-seed/seed-1.6-20250625": { "date": "2026-01-19 00:00:00", "model_permaslug": "bytedance-seed/seed-1.6-20250625", "variant": "standard", "variant_permaslug": "bytedance-seed/seed-1.6-20250625", "count": 1953211, "total_completion_tokens": 758325790, "total_prompt_tokens": 9583367290, "total_native_tokens_reasoning": 529830307, "num_media_prompt": 1898597, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2713, "requests_with_tool_call_errors": 80 }, "openai/gpt-3.5-turbo": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-3.5-turbo", "variant": "standard", "variant_permaslug": "openai/gpt-3.5-turbo", "count": 674562, "total_completion_tokens": 103912194, "total_prompt_tokens": 472478631, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 16655, "requests_with_tool_call_errors": 929 }, "tngtech/deepseek-r1t-chimera:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/deepseek-r1t-chimera", "variant": "free", "variant_permaslug": "tngtech/deepseek-r1t-chimera:free", "count": 2216079, "total_completion_tokens": 1296023240, "total_prompt_tokens": 24526317860, "total_native_tokens_reasoning": 25951771, "num_media_prompt": 99, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5155309829, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen-2.5-7b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-2.5-7b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen-2.5-7b-instruct", "count": 5445718, "total_completion_tokens": 845301347, "total_prompt_tokens": 5055046507, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1143, "requests_with_tool_call_errors": 187 }, "openai/gpt-5-2025-08-07": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-2025-08-07", "variant": "standard", "variant_permaslug": "openai/gpt-5-2025-08-07", "count": 2830941, "total_completion_tokens": 3818817390, "total_prompt_tokens": 27987719813, "total_native_tokens_reasoning": 3052967172, "num_media_prompt": 7145576, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 13494982272, "total_tool_calls": 670869, "requests_with_tool_call_errors": 3925 }, "qwen/qwen3-coder-30b-a3b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-coder-30b-a3b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen3-coder-30b-a3b-instruct", "count": 698464, "total_completion_tokens": 231072212, "total_prompt_tokens": 3614654628, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 196460, "requests_with_tool_call_errors": 71456 }, "qwen/qwen-2.5-72b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-2.5-72b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen-2.5-72b-instruct", "count": 2513332, "total_completion_tokens": 202680254, "total_prompt_tokens": 2512435745, "total_native_tokens_reasoning": 0, "num_media_prompt": 4, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 57271519, "total_tool_calls": 26022, "requests_with_tool_call_errors": 463 }, "meta-llama/llama-3.2-3b-instruct:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.2-3b-instruct", "variant": "free", "variant_permaslug": "meta-llama/llama-3.2-3b-instruct:free", "count": 75948, "total_completion_tokens": 16885186, "total_prompt_tokens": 72099472, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4.1-mini-2025-04-14": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4.1-mini-2025-04-14", "variant": "standard", "variant_permaslug": "openai/gpt-4.1-mini-2025-04-14", "count": 24327807, "total_completion_tokens": 4068177973, "total_prompt_tokens": 50078864170, "total_native_tokens_reasoning": 0, "num_media_prompt": 2969440, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 12610175616, "total_tool_calls": 2294321, "requests_with_tool_call_errors": 12164 }, "meta-llama/llama-guard-2-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-guard-2-8b", "variant": "standard", "variant_permaslug": "meta-llama/llama-guard-2-8b", "count": 56266, "total_completion_tokens": 96360, "total_prompt_tokens": 771577, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "eleutherai/llemma_7b": { "date": "2026-01-19 00:00:00", "model_permaslug": "eleutherai/llemma_7b", "variant": "standard", "variant_permaslug": "eleutherai/llemma_7b", "count": 1033, "total_completion_tokens": 1468344, "total_prompt_tokens": 493084, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/o1-2024-12-17": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o1-2024-12-17", "variant": "standard", "variant_permaslug": "openai/o1-2024-12-17", "count": 7565, "total_completion_tokens": 19949444, "total_prompt_tokens": 108413923, "total_native_tokens_reasoning": 16314752, "num_media_prompt": 585, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 73294720, "total_tool_calls": 224, "requests_with_tool_call_errors": 0 }, "nousresearch/hermes-4-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-4-70b", "variant": "standard", "variant_permaslug": "nousresearch/hermes-4-70b", "count": 307624, "total_completion_tokens": 55744604, "total_prompt_tokens": 1379930871, "total_native_tokens_reasoning": 984015, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 139212784, "total_tool_calls": 422, "requests_with_tool_call_errors": 4 }, "qwen/qwen-plus-2025-07-28:thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-plus-2025-07-28", "variant": "thinking", "variant_permaslug": "qwen/qwen-plus-2025-07-28:thinking", "count": 3125, "total_completion_tokens": 5867030, "total_prompt_tokens": 19394762, "total_native_tokens_reasoning": 4300735, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 390, "requests_with_tool_call_errors": 2 }, "bytedance-seed/seed-1.6-flash-20250625": { "date": "2026-01-19 00:00:00", "model_permaslug": "bytedance-seed/seed-1.6-flash-20250625", "variant": "standard", "variant_permaslug": "bytedance-seed/seed-1.6-flash-20250625", "count": 232087, "total_completion_tokens": 243753976, "total_prompt_tokens": 662542096, "total_native_tokens_reasoning": 183485749, "num_media_prompt": 145834, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 5248, "requests_with_tool_call_errors": 464 }, "meta-llama/llama-3.3-70b-instruct:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.3-70b-instruct", "variant": "free", "variant_permaslug": "meta-llama/llama-3.3-70b-instruct:free", "count": 1060390, "total_completion_tokens": 518883679, "total_prompt_tokens": 3896419811, "total_native_tokens_reasoning": 0, "num_media_prompt": 11, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 9431, "requests_with_tool_call_errors": 3658 }, "intfloat/e5-base-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "intfloat/e5-base-v2-20251117", "variant": "standard", "variant_permaslug": "intfloat/e5-base-v2-20251117", "count": 21742, "total_completion_tokens": 0, "total_prompt_tokens": 120121303, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "alibaba/tongyi-deepresearch-30b-a3b": { "date": "2026-01-19 00:00:00", "model_permaslug": "alibaba/tongyi-deepresearch-30b-a3b", "variant": "standard", "variant_permaslug": "alibaba/tongyi-deepresearch-30b-a3b", "count": 236834, "total_completion_tokens": 159388547, "total_prompt_tokens": 2997498734, "total_native_tokens_reasoning": 120512990, "num_media_prompt": 173, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1932252627, "total_tool_calls": 4531, "requests_with_tool_call_errors": 1278 }, "openai/o4-mini-2025-04-16": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o4-mini-2025-04-16", "variant": "standard", "variant_permaslug": "openai/o4-mini-2025-04-16", "count": 327193, "total_completion_tokens": 318907346, "total_prompt_tokens": 1421212071, "total_native_tokens_reasoning": 258876792, "num_media_prompt": 107216, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 508844672, "total_tool_calls": 28437, "requests_with_tool_call_errors": 13 }, "baai/bge-m3-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "baai/bge-m3-20251117", "variant": "standard", "variant_permaslug": "baai/bge-m3-20251117", "count": 2023152, "total_completion_tokens": 0, "total_prompt_tokens": 2243444441, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sentence-transformers/all-minilm-l6-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "sentence-transformers/all-minilm-l6-v2-20251117", "variant": "standard", "variant_permaslug": "sentence-transformers/all-minilm-l6-v2-20251117", "count": 1034419, "total_completion_tokens": 0, "total_prompt_tokens": 510912366, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "intfloat/e5-large-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "intfloat/e5-large-v2-20251117", "variant": "standard", "variant_permaslug": "intfloat/e5-large-v2-20251117", "count": 87715, "total_completion_tokens": 0, "total_prompt_tokens": 173189236, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-max": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-max", "variant": "standard", "variant_permaslug": "qwen/qwen3-max", "count": 267185, "total_completion_tokens": 99759200, "total_prompt_tokens": 1672265257, "total_native_tokens_reasoning": 0, "num_media_prompt": 155, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 45959, "requests_with_tool_call_errors": 949 }, "liquid/lfm-2.2-6b": { "date": "2026-01-19 00:00:00", "model_permaslug": "liquid/lfm-2.2-6b", "variant": "standard", "variant_permaslug": "liquid/lfm-2.2-6b", "count": 570850, "total_completion_tokens": 24984489, "total_prompt_tokens": 129744763, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-oss-20b:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-20b", "variant": "free", "variant_permaslug": "openai/gpt-oss-20b:free", "count": 145945, "total_completion_tokens": 147121633, "total_prompt_tokens": 651986603, "total_native_tokens_reasoning": 117888105, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 11581, "requests_with_tool_call_errors": 1157 }, "google/gemini-3-pro-image-preview-20251120": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-3-pro-image-preview-20251120", "variant": "standard", "variant_permaslug": "google/gemini-3-pro-image-preview-20251120", "count": 2037408, "total_completion_tokens": 2871158702, "total_prompt_tokens": 2794742882, "total_native_tokens_reasoning": 633048425, "num_media_prompt": 2690156, "num_media_completion": 2415325, "num_audio_prompt": 0, "total_native_tokens_cached": 14718890, "total_tool_calls": 214, "requests_with_tool_call_errors": 214 }, "nvidia/llama-3.3-nemotron-super-49b-v1.5": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "variant": "standard", "variant_permaslug": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "count": 74333, "total_completion_tokens": 77139766, "total_prompt_tokens": 524614552, "total_native_tokens_reasoning": 70163431, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2306, "requests_with_tool_call_errors": 51 }, "qwen/qwen3-30b-a3b-instruct-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-30b-a3b-instruct-2507", "variant": "standard", "variant_permaslug": "qwen/qwen3-30b-a3b-instruct-2507", "count": 2063244, "total_completion_tokens": 834251470, "total_prompt_tokens": 7368588974, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1224026004, "total_tool_calls": 30764, "requests_with_tool_call_errors": 2349 }, "allenai/molmo-2-8b-20260109:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/molmo-2-8b-20260109", "variant": "free", "variant_permaslug": "allenai/molmo-2-8b-20260109:free", "count": 127448, "total_completion_tokens": 37719244, "total_prompt_tokens": 289344552, "total_native_tokens_reasoning": 0, "num_media_prompt": 45806, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-235b-a22b-thinking-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-235b-a22b-thinking-2507", "variant": "standard", "variant_permaslug": "qwen/qwen3-235b-a22b-thinking-2507", "count": 574641, "total_completion_tokens": 810562842, "total_prompt_tokens": 2424528103, "total_native_tokens_reasoning": 656760281, "num_media_prompt": 15, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 449322789, "total_tool_calls": 73531, "requests_with_tool_call_errors": 16746 }, "mistralai/mistral-large-2512": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-large-2512", "variant": "standard", "variant_permaslug": "mistralai/mistral-large-2512", "count": 1184978, "total_completion_tokens": 334998151, "total_prompt_tokens": 3961659617, "total_native_tokens_reasoning": 0, "num_media_prompt": 91815, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 171074, "requests_with_tool_call_errors": 1924 }, "openai/o3-mini-2025-01-31": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o3-mini-2025-01-31", "variant": "standard", "variant_permaslug": "openai/o3-mini-2025-01-31", "count": 308328, "total_completion_tokens": 478951917, "total_prompt_tokens": 914607310, "total_native_tokens_reasoning": 353225920, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 323890048, "total_tool_calls": 2383, "requests_with_tool_call_errors": 41 }, "cohere/command-r7b-12-2024": { "date": "2026-01-19 00:00:00", "model_permaslug": "cohere/command-r7b-12-2024", "variant": "standard", "variant_permaslug": "cohere/command-r7b-12-2024", "count": 1803098, "total_completion_tokens": 193474379, "total_prompt_tokens": 8891742751, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "allenai/olmo-3.1-32b-think-20251215": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/olmo-3.1-32b-think-20251215", "variant": "standard", "variant_permaslug": "allenai/olmo-3.1-32b-think-20251215", "count": 45650, "total_completion_tokens": 150533469, "total_prompt_tokens": 255774740, "total_native_tokens_reasoning": 131134929, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 52961424, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "z-ai/glm-4.6": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.6", "variant": "standard", "variant_permaslug": "z-ai/glm-4.6", "count": 2197581, "total_completion_tokens": 1222724976, "total_prompt_tokens": 21446182073, "total_native_tokens_reasoning": 577591342, "num_media_prompt": 619, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 9314347785, "total_tool_calls": 278257, "requests_with_tool_call_errors": 46725 }, "tngtech/deepseek-r1t-chimera": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/deepseek-r1t-chimera", "variant": "standard", "variant_permaslug": "tngtech/deepseek-r1t-chimera", "count": 263909, "total_completion_tokens": 35306418, "total_prompt_tokens": 1622203375, "total_native_tokens_reasoning": 63773, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 345665658, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemma-3-4b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-4b-it", "variant": "standard", "variant_permaslug": "google/gemma-3-4b-it", "count": 24773822, "total_completion_tokens": 751915995, "total_prompt_tokens": 1675871487, "total_native_tokens_reasoning": 0, "num_media_prompt": 73222, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 262326656, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nvidia/nemotron-nano-12b-v2-vl": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-nano-12b-v2-vl", "variant": "standard", "variant_permaslug": "nvidia/nemotron-nano-12b-v2-vl", "count": 18716, "total_completion_tokens": 12551625, "total_prompt_tokens": 44388396, "total_native_tokens_reasoning": 10692719, "num_media_prompt": 15800, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepseek/deepseek-r1-0528:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-r1-0528", "variant": "free", "variant_permaslug": "deepseek/deepseek-r1-0528:free", "count": 1846716, "total_completion_tokens": 1452388540, "total_prompt_tokens": 12305184584, "total_native_tokens_reasoning": 984705588, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3506951461, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-7b-instruct-v0.2": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-7b-instruct-v0.2", "variant": "standard", "variant_permaslug": "mistralai/mistral-7b-instruct-v0.2", "count": 150723, "total_completion_tokens": 6322315, "total_prompt_tokens": 35927934, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "tngtech/deepseek-r1t2-chimera:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/deepseek-r1t2-chimera", "variant": "free", "variant_permaslug": "tngtech/deepseek-r1t2-chimera:free", "count": 9630252, "total_completion_tokens": 8662919705, "total_prompt_tokens": 91499670433, "total_native_tokens_reasoning": 4908855415, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 10961445632, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5.2-chat-20251211": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.2-chat-20251211", "variant": "standard", "variant_permaslug": "openai/gpt-5.2-chat-20251211", "count": 1781502, "total_completion_tokens": 533931783, "total_prompt_tokens": 7823169333, "total_native_tokens_reasoning": 126747456, "num_media_prompt": 662583, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3667900288, "total_tool_calls": 70523, "requests_with_tool_call_errors": 1272 }, "sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117", "variant": "standard", "variant_permaslug": "sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117", "count": 34496, "total_completion_tokens": 0, "total_prompt_tokens": 64365618, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-large": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-large", "variant": "standard", "variant_permaslug": "mistralai/mistral-large", "count": 109155, "total_completion_tokens": 25331326, "total_prompt_tokens": 448581208, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 2442, "requests_with_tool_call_errors": 28 }, "qwen/qwen3-8b-04-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-8b-04-28", "variant": "standard", "variant_permaslug": "qwen/qwen3-8b-04-28", "count": 1083088, "total_completion_tokens": 1302577216, "total_prompt_tokens": 1510351462, "total_native_tokens_reasoning": 1130728655, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 366149808, "total_tool_calls": 10884, "requests_with_tool_call_errors": 225 }, "tngtech/tng-r1t-chimera:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "tngtech/tng-r1t-chimera", "variant": "free", "variant_permaslug": "tngtech/tng-r1t-chimera:free", "count": 727919, "total_completion_tokens": 571752368, "total_prompt_tokens": 7849838046, "total_native_tokens_reasoning": 351126255, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1461032576, "total_tool_calls": 5974, "requests_with_tool_call_errors": 355 }, "liquid/lfm2-8b-a1b": { "date": "2026-01-19 00:00:00", "model_permaslug": "liquid/lfm2-8b-a1b", "variant": "standard", "variant_permaslug": "liquid/lfm2-8b-a1b", "count": 66606, "total_completion_tokens": 6376575, "total_prompt_tokens": 48372223, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "x-ai/grok-4-07-09": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-4-07-09", "variant": "standard", "variant_permaslug": "x-ai/grok-4-07-09", "count": 692491, "total_completion_tokens": 1156269714, "total_prompt_tokens": 4570323962, "total_native_tokens_reasoning": 837979893, "num_media_prompt": 200193, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2163902788, "total_tool_calls": 73817, "requests_with_tool_call_errors": 2060 }, "google/gemma-3-4b-it:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-4b-it", "variant": "free", "variant_permaslug": "google/gemma-3-4b-it:free", "count": 54683, "total_completion_tokens": 0, "total_prompt_tokens": 48827034, "total_native_tokens_reasoning": 0, "num_media_prompt": 57435, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sao10k/l3-lunaris-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "sao10k/l3-lunaris-8b", "variant": "standard", "variant_permaslug": "sao10k/l3-lunaris-8b", "count": 2450856, "total_completion_tokens": 516022859, "total_prompt_tokens": 6360572820, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "venice/uncensored:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "venice/uncensored", "variant": "free", "variant_permaslug": "venice/uncensored:free", "count": 143030, "total_completion_tokens": 59610815, "total_prompt_tokens": 380872557, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "perplexity/sonar-reasoning-pro": { "date": "2026-01-19 00:00:00", "model_permaslug": "perplexity/sonar-reasoning-pro", "variant": "standard", "variant_permaslug": "perplexity/sonar-reasoning-pro", "count": 37766, "total_completion_tokens": 42295554, "total_prompt_tokens": 106684128, "total_native_tokens_reasoning": 0, "num_media_prompt": 787, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-embedding-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-embedding-8b", "variant": "standard", "variant_permaslug": "qwen/qwen3-embedding-8b", "count": 13466551, "total_completion_tokens": 0, "total_prompt_tokens": 21635509665, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthracite-org/magnum-v4-72b": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthracite-org/magnum-v4-72b", "variant": "standard", "variant_permaslug": "anthracite-org/magnum-v4-72b", "count": 21113, "total_completion_tokens": 3540860, "total_prompt_tokens": 45799893, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-vl-30b-a3b-thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-30b-a3b-thinking", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-30b-a3b-thinking", "count": 21696, "total_completion_tokens": 50113408, "total_prompt_tokens": 74105043, "total_native_tokens_reasoning": 42125107, "num_media_prompt": 23614, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1510, "requests_with_tool_call_errors": 128 }, "mistralai/mistral-small-24b-instruct-2501": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-small-24b-instruct-2501", "variant": "standard", "variant_permaslug": "mistralai/mistral-small-24b-instruct-2501", "count": 6960859, "total_completion_tokens": 1225370908, "total_prompt_tokens": 14255863011, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 59745005, "total_tool_calls": 1131, "requests_with_tool_call_errors": 159 }, "z-ai/glm-4.6:exacto": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.6", "variant": "exacto", "variant_permaslug": "z-ai/glm-4.6:exacto", "count": 46944, "total_completion_tokens": 24832165, "total_prompt_tokens": 601696080, "total_native_tokens_reasoning": 15036207, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 289442169, "total_tool_calls": 15527, "requests_with_tool_call_errors": 4019 }, "alpindale/goliath-120b": { "date": "2026-01-19 00:00:00", "model_permaslug": "alpindale/goliath-120b", "variant": "standard", "variant_permaslug": "alpindale/goliath-120b", "count": 3858, "total_completion_tokens": 1106171, "total_prompt_tokens": 3636492, "total_native_tokens_reasoning": 0, "num_media_prompt": 2, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/pixtral-12b": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/pixtral-12b", "variant": "standard", "variant_permaslug": "mistralai/pixtral-12b", "count": 132130, "total_completion_tokens": 9452448, "total_prompt_tokens": 65159498, "total_native_tokens_reasoning": 0, "num_media_prompt": 58379, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 57, "requests_with_tool_call_errors": 8 }, "qwen/qwen3-vl-8b-thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-8b-thinking", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-8b-thinking", "count": 9516, "total_completion_tokens": 46908484, "total_prompt_tokens": 47136515, "total_native_tokens_reasoning": 43226360, "num_media_prompt": 19536, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 178, "requests_with_tool_call_errors": 39 }, "openai/gpt-5.1-codex-mini-20251113": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.1-codex-mini-20251113", "variant": "standard", "variant_permaslug": "openai/gpt-5.1-codex-mini-20251113", "count": 186557, "total_completion_tokens": 164996341, "total_prompt_tokens": 4691133466, "total_native_tokens_reasoning": 123890587, "num_media_prompt": 19093, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3905151488, "total_tool_calls": 77815, "requests_with_tool_call_errors": 430 }, "meta-llama/llama-3.1-405b": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.1-405b", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.1-405b", "count": 10499, "total_completion_tokens": 3652834, "total_prompt_tokens": 56848, "total_native_tokens_reasoning": 0, "num_media_prompt": 1, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nousresearch/hermes-3-llama-3.1-405b:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-3-llama-3.1-405b", "variant": "free", "variant_permaslug": "nousresearch/hermes-3-llama-3.1-405b:free", "count": 60782, "total_completion_tokens": 11984095, "total_prompt_tokens": 312277154, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-medium-3.1": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-medium-3.1", "variant": "standard", "variant_permaslug": "mistralai/mistral-medium-3.1", "count": 390184, "total_completion_tokens": 184880154, "total_prompt_tokens": 3874645996, "total_native_tokens_reasoning": 0, "num_media_prompt": 20110, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 17651, "requests_with_tool_call_errors": 1506 }, "google/gemini-2.0-flash-001": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.0-flash-001", "variant": "standard", "variant_permaslug": "google/gemini-2.0-flash-001", "count": 136992641, "total_completion_tokens": 17924314182, "total_prompt_tokens": 158559212770, "total_native_tokens_reasoning": 0, "num_media_prompt": 12036456, "num_media_completion": 0, "num_audio_prompt": 47410, "total_native_tokens_cached": 998000777, "total_tool_calls": 1693902, "requests_with_tool_call_errors": 13063 }, "deepseek/deepseek-r1": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-r1", "variant": "standard", "variant_permaslug": "deepseek/deepseek-r1", "count": 779151, "total_completion_tokens": 1077354518, "total_prompt_tokens": 3152973582, "total_native_tokens_reasoning": 585244280, "num_media_prompt": 124, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 10581056, "total_tool_calls": 30082, "requests_with_tool_call_errors": 1045 }, "qwen/qwen3-vl-8b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-8b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-8b-instruct", "count": 7781731, "total_completion_tokens": 1421861558, "total_prompt_tokens": 8594391654, "total_native_tokens_reasoning": 0, "num_media_prompt": 7434328, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 160562528, "total_tool_calls": 86278, "requests_with_tool_call_errors": 3374 }, "mistralai/mistral-7b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-7b-instruct", "variant": "standard", "variant_permaslug": "mistralai/mistral-7b-instruct", "count": 511372, "total_completion_tokens": 73436658, "total_prompt_tokens": 485394721, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthropic/claude-4.5-sonnet-20250929": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4.5-sonnet-20250929", "variant": "standard", "variant_permaslug": "anthropic/claude-4.5-sonnet-20250929", "count": 23485779, "total_completion_tokens": 12344009204, "total_prompt_tokens": 781245834164, "total_native_tokens_reasoning": 509278025, "num_media_prompt": 6006596, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 507231193823, "total_tool_calls": 9001911, "requests_with_tool_call_errors": 221803 }, "qwen/qwen2.5-vl-32b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen2.5-vl-32b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen2.5-vl-32b-instruct", "count": 645588, "total_completion_tokens": 89811420, "total_prompt_tokens": 1986167487, "total_native_tokens_reasoning": 0, "num_media_prompt": 557308, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 84296080, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "ibm-granite/granite-4.0-h-micro": { "date": "2026-01-19 00:00:00", "model_permaslug": "ibm-granite/granite-4.0-h-micro", "variant": "standard", "variant_permaslug": "ibm-granite/granite-4.0-h-micro", "count": 402059, "total_completion_tokens": 48029034, "total_prompt_tokens": 655467559, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-audio-mini": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-audio-mini", "variant": "standard", "variant_permaslug": "openai/gpt-audio-mini", "count": 4688, "total_completion_tokens": 2428037, "total_prompt_tokens": 2105169, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 1958, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mixtral-8x7b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mixtral-8x7b-instruct", "variant": "standard", "variant_permaslug": "mistralai/mixtral-8x7b-instruct", "count": 8090801, "total_completion_tokens": 2324745397, "total_prompt_tokens": 1691311580, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 6, "requests_with_tool_call_errors": 4 }, "google/gemma-3-12b-it:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-12b-it", "variant": "free", "variant_permaslug": "google/gemma-3-12b-it:free", "count": 66238, "total_completion_tokens": 0, "total_prompt_tokens": 54791449, "total_native_tokens_reasoning": 0, "num_media_prompt": 34318, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "allenai/olmo-2-0325-32b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "allenai/olmo-2-0325-32b-instruct", "variant": "standard", "variant_permaslug": "allenai/olmo-2-0325-32b-instruct", "count": 119, "total_completion_tokens": 17925, "total_prompt_tokens": 166416, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "aion-labs/aion-1.0-mini": { "date": "2026-01-19 00:00:00", "model_permaslug": "aion-labs/aion-1.0-mini", "variant": "standard", "variant_permaslug": "aion-labs/aion-1.0-mini", "count": 1749, "total_completion_tokens": 690580, "total_prompt_tokens": 2297110, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4o-2024-08-06": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-2024-08-06", "variant": "standard", "variant_permaslug": "openai/gpt-4o-2024-08-06", "count": 278969, "total_completion_tokens": 32496053, "total_prompt_tokens": 338646842, "total_native_tokens_reasoning": 0, "num_media_prompt": 19647, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 83269120, "total_tool_calls": 3489, "requests_with_tool_call_errors": 447 }, "mistralai/codestral-2508": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/codestral-2508", "variant": "standard", "variant_permaslug": "mistralai/codestral-2508", "count": 2232296, "total_completion_tokens": 336877942, "total_prompt_tokens": 3384393093, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1960, "requests_with_tool_call_errors": 57 }, "google/gemini-2.5-flash-lite": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-flash-lite", "variant": "standard", "variant_permaslug": "google/gemini-2.5-flash-lite", "count": 103426441, "total_completion_tokens": 31659875717, "total_prompt_tokens": 260309030001, "total_native_tokens_reasoning": 1608199600, "num_media_prompt": 212189808, "num_media_completion": 0, "num_audio_prompt": 23226, "total_native_tokens_cached": 41116052668, "total_tool_calls": 2281661, "requests_with_tool_call_errors": 171902 }, "openai/o3-pro-2025-06-10": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o3-pro-2025-06-10", "variant": "standard", "variant_permaslug": "openai/o3-pro-2025-06-10", "count": 3337, "total_completion_tokens": 2054818, "total_prompt_tokens": 15243698, "total_native_tokens_reasoning": 1054189, "num_media_prompt": 208, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1459, "requests_with_tool_call_errors": 0 }, "sentence-transformers/paraphrase-minilm-l6-v2-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "sentence-transformers/paraphrase-minilm-l6-v2-20251117", "variant": "standard", "variant_permaslug": "sentence-transformers/paraphrase-minilm-l6-v2-20251117", "count": 20601, "total_completion_tokens": 0, "total_prompt_tokens": 76404005, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mistral-large-2411": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-large-2411", "variant": "standard", "variant_permaslug": "mistralai/mistral-large-2411", "count": 69392, "total_completion_tokens": 20364448, "total_prompt_tokens": 250051299, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1567, "requests_with_tool_call_errors": 30 }, "openai/gpt-4-1106-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4-1106-preview", "variant": "standard", "variant_permaslug": "openai/gpt-4-1106-preview", "count": 29639, "total_completion_tokens": 3002692, "total_prompt_tokens": 19826741, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 8832, "requests_with_tool_call_errors": 4 }, "moonshotai/kimi-k2-0905": { "date": "2026-01-19 00:00:00", "model_permaslug": "moonshotai/kimi-k2-0905", "variant": "standard", "variant_permaslug": "moonshotai/kimi-k2-0905", "count": 11476713, "total_completion_tokens": 1649528478, "total_prompt_tokens": 26469505503, "total_native_tokens_reasoning": 0, "num_media_prompt": 344, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3829086178, "total_tool_calls": 74087, "requests_with_tool_call_errors": 1219 }, "openai/gpt-4": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4", "variant": "standard", "variant_permaslug": "openai/gpt-4", "count": 136521, "total_completion_tokens": 14150269, "total_prompt_tokens": 140665510, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1395584, "total_tool_calls": 3478, "requests_with_tool_call_errors": 212 }, "mistralai/ministral-3b": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/ministral-3b", "variant": "standard", "variant_permaslug": "mistralai/ministral-3b", "count": 6329793, "total_completion_tokens": 312850241, "total_prompt_tokens": 4947849276, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 146, "requests_with_tool_call_errors": 8 }, "qwen/qwen-max-2025-01-25": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-max-2025-01-25", "variant": "standard", "variant_permaslug": "qwen/qwen-max-2025-01-25", "count": 60834, "total_completion_tokens": 10322415, "total_prompt_tokens": 107420863, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 629504, "total_tool_calls": 2245, "requests_with_tool_call_errors": 81 }, "anthropic/claude-3-5-haiku": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-3-5-haiku", "variant": "standard", "variant_permaslug": "anthropic/claude-3-5-haiku", "count": 4618564, "total_completion_tokens": 551549329, "total_prompt_tokens": 9445989016, "total_native_tokens_reasoning": 0, "num_media_prompt": 42768, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1200291032, "total_tool_calls": 124276, "requests_with_tool_call_errors": 2694 }, "google/gemma-3n-e2b-it:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3n-e2b-it", "variant": "free", "variant_permaslug": "google/gemma-3n-e2b-it:free", "count": 100981, "total_completion_tokens": 34038123, "total_prompt_tokens": 19350483, "total_native_tokens_reasoning": 0, "num_media_prompt": 8, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4-0314": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4-0314", "variant": "standard", "variant_permaslug": "openai/gpt-4-0314", "count": 1639, "total_completion_tokens": 361835, "total_prompt_tokens": 806148, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sao10k/l3-euryale-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "sao10k/l3-euryale-70b", "variant": "standard", "variant_permaslug": "sao10k/l3-euryale-70b", "count": 25751, "total_completion_tokens": 7455897, "total_prompt_tokens": 30895033, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "baidu/ernie-4.5-21b-a3b-thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "baidu/ernie-4.5-21b-a3b-thinking", "variant": "standard", "variant_permaslug": "baidu/ernie-4.5-21b-a3b-thinking", "count": 6119, "total_completion_tokens": 13871945, "total_prompt_tokens": 17060944, "total_native_tokens_reasoning": 11987443, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nex-agi/deepseek-v3.1-nex-n1": { "date": "2026-01-19 00:00:00", "model_permaslug": "nex-agi/deepseek-v3.1-nex-n1", "variant": "standard", "variant_permaslug": "nex-agi/deepseek-v3.1-nex-n1", "count": 237341, "total_completion_tokens": 143737138, "total_prompt_tokens": 3172479375, "total_native_tokens_reasoning": 0, "num_media_prompt": 205, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 6124, "requests_with_tool_call_errors": 186 }, "qwen/qwen3-235b-a22b-07-25": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-235b-a22b-07-25", "variant": "standard", "variant_permaslug": "qwen/qwen3-235b-a22b-07-25", "count": 27738550, "total_completion_tokens": 5143603685, "total_prompt_tokens": 65756794705, "total_native_tokens_reasoning": 0, "num_media_prompt": 350, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 15195637496, "total_tool_calls": 376745, "requests_with_tool_call_errors": 10763 }, "nousresearch/hermes-4-405b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-4-405b", "variant": "standard", "variant_permaslug": "nousresearch/hermes-4-405b", "count": 100190, "total_completion_tokens": 18994938, "total_prompt_tokens": 418466375, "total_native_tokens_reasoning": 1800661, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemma-3n-e4b-it:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3n-e4b-it", "variant": "free", "variant_permaslug": "google/gemma-3n-e4b-it:free", "count": 26921, "total_completion_tokens": 7602874, "total_prompt_tokens": 14573881, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthropic/claude-3.5-sonnet": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-3.5-sonnet", "variant": "standard", "variant_permaslug": "anthropic/claude-3.5-sonnet", "count": 1163025, "total_completion_tokens": 319390574, "total_prompt_tokens": 4403983689, "total_native_tokens_reasoning": 0, "num_media_prompt": 85333, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1195679087, "total_tool_calls": 73869, "requests_with_tool_call_errors": 3326 }, "openai/gpt-4o-mini-search-preview-2025-03-11": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o-mini-search-preview-2025-03-11", "variant": "standard", "variant_permaslug": "openai/gpt-4o-mini-search-preview-2025-03-11", "count": 76615, "total_completion_tokens": 65653693, "total_prompt_tokens": 43376909, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mancer/weaver": { "date": "2026-01-19 00:00:00", "model_permaslug": "mancer/weaver", "variant": "standard", "variant_permaslug": "mancer/weaver", "count": 3285, "total_completion_tokens": 1488561, "total_prompt_tokens": 2836050, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "deepcogito/cogito-v2-preview-llama-109b-moe": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepcogito/cogito-v2-preview-llama-109b-moe", "variant": "standard", "variant_permaslug": "deepcogito/cogito-v2-preview-llama-109b-moe", "count": 10123, "total_completion_tokens": 1154296, "total_prompt_tokens": 32992630, "total_native_tokens_reasoning": 174120, "num_media_prompt": 11384, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 7, "requests_with_tool_call_errors": 0 }, "nousresearch/hermes-3-llama-3.1-405b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-3-llama-3.1-405b", "variant": "standard", "variant_permaslug": "nousresearch/hermes-3-llama-3.1-405b", "count": 412952, "total_completion_tokens": 115254765, "total_prompt_tokens": 850007155, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nvidia/nemotron-nano-9b-v2:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "nvidia/nemotron-nano-9b-v2", "variant": "free", "variant_permaslug": "nvidia/nemotron-nano-9b-v2:free", "count": 75121, "total_completion_tokens": 76730359, "total_prompt_tokens": 283722712, "total_native_tokens_reasoning": 51109614, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 3452, "requests_with_tool_call_errors": 587 }, "qwen/qwen3-next-80b-a3b-instruct-2509:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-next-80b-a3b-instruct-2509", "variant": "free", "variant_permaslug": "qwen/qwen3-next-80b-a3b-instruct-2509:free", "count": 57796, "total_completion_tokens": 21857390, "total_prompt_tokens": 563875735, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 4455, "requests_with_tool_call_errors": 532 }, "moonshotai/kimi-k2-0905:exacto": { "date": "2026-01-19 00:00:00", "model_permaslug": "moonshotai/kimi-k2-0905", "variant": "exacto", "variant_permaslug": "moonshotai/kimi-k2-0905:exacto", "count": 723895, "total_completion_tokens": 213242986, "total_prompt_tokens": 1141531777, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 701288253, "total_tool_calls": 14413, "requests_with_tool_call_errors": 121 }, "deepseek/deepseek-chat-v3-0324": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-chat-v3-0324", "variant": "standard", "variant_permaslug": "deepseek/deepseek-chat-v3-0324", "count": 27919785, "total_completion_tokens": 5316434896, "total_prompt_tokens": 107114035100, "total_native_tokens_reasoning": 0, "num_media_prompt": 254, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 7243824223, "total_tool_calls": 35501, "requests_with_tool_call_errors": 2224 }, "openai/gpt-3.5-turbo-16k": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-3.5-turbo-16k", "variant": "standard", "variant_permaslug": "openai/gpt-3.5-turbo-16k", "count": 41646, "total_completion_tokens": 6041361, "total_prompt_tokens": 40272129, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 12065, "requests_with_tool_call_errors": 77 }, "anthropic/claude-3-7-sonnet-20250219": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-3-7-sonnet-20250219", "variant": "standard", "variant_permaslug": "anthropic/claude-3-7-sonnet-20250219", "count": 2926565, "total_completion_tokens": 1391260505, "total_prompt_tokens": 27324106988, "total_native_tokens_reasoning": 13691552, "num_media_prompt": 222530, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 8427258210, "total_tool_calls": 181055, "requests_with_tool_call_errors": 4546 }, "openai/chatgpt-4o-latest": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/chatgpt-4o-latest", "variant": "standard", "variant_permaslug": "openai/chatgpt-4o-latest", "count": 415332, "total_completion_tokens": 108526462, "total_prompt_tokens": 1339527331, "total_native_tokens_reasoning": 0, "num_media_prompt": 107281, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "meta-llama/llama-3.2-3b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.2-3b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.2-3b-instruct", "count": 7385388, "total_completion_tokens": 1935843119, "total_prompt_tokens": 6590530751, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen-2-vl-7b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-2-vl-7b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen-2-vl-7b-instruct", "count": 305972, "total_completion_tokens": 28945407, "total_prompt_tokens": 259862256, "total_native_tokens_reasoning": 0, "num_media_prompt": 274682, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/text-embedding-3-large": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/text-embedding-3-large", "variant": "standard", "variant_permaslug": "openai/text-embedding-3-large", "count": 5340977, "total_completion_tokens": 0, "total_prompt_tokens": 4071224619, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "moonshotai/kimi-k2": { "date": "2026-01-19 00:00:00", "model_permaslug": "moonshotai/kimi-k2", "variant": "standard", "variant_permaslug": "moonshotai/kimi-k2", "count": 1103050, "total_completion_tokens": 221770044, "total_prompt_tokens": 3212174918, "total_native_tokens_reasoning": 0, "num_media_prompt": 11, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1618420451, "total_tool_calls": 43497, "requests_with_tool_call_errors": 618 }, "thedrummer/skyfall-36b-v2": { "date": "2026-01-19 00:00:00", "model_permaslug": "thedrummer/skyfall-36b-v2", "variant": "standard", "variant_permaslug": "thedrummer/skyfall-36b-v2", "count": 372206, "total_completion_tokens": 114033104, "total_prompt_tokens": 1133099759, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 681424848, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "x-ai/grok-4-fast": { "date": "2026-01-19 00:00:00", "model_permaslug": "x-ai/grok-4-fast", "variant": "standard", "variant_permaslug": "x-ai/grok-4-fast", "count": 30662938, "total_completion_tokens": 26956873712, "total_prompt_tokens": 139154030110, "total_native_tokens_reasoning": 14821789705, "num_media_prompt": 2345367, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 31193574569, "total_tool_calls": 722986, "requests_with_tool_call_errors": 1470 }, "openai/gpt-5.1-20251113": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.1-20251113", "variant": "standard", "variant_permaslug": "openai/gpt-5.1-20251113", "count": 2665874, "total_completion_tokens": 3226437362, "total_prompt_tokens": 22140881048, "total_native_tokens_reasoning": 1928406314, "num_media_prompt": 1407067, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 7851680896, "total_tool_calls": 221243, "requests_with_tool_call_errors": 4487 }, "openai/gpt-4o": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4o", "variant": "standard", "variant_permaslug": "openai/gpt-4o", "count": 7199508, "total_completion_tokens": 921141443, "total_prompt_tokens": 12678725365, "total_native_tokens_reasoning": 0, "num_media_prompt": 861698, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 3747912448, "total_tool_calls": 487300, "requests_with_tool_call_errors": 12787 }, "baai/bge-base-en-v1.5-20251117": { "date": "2026-01-19 00:00:00", "model_permaslug": "baai/bge-base-en-v1.5-20251117", "variant": "standard", "variant_permaslug": "baai/bge-base-en-v1.5-20251117", "count": 12236, "total_completion_tokens": 0, "total_prompt_tokens": 26346034, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4.1-nano-2025-04-14": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4.1-nano-2025-04-14", "variant": "standard", "variant_permaslug": "openai/gpt-4.1-nano-2025-04-14", "count": 9125773, "total_completion_tokens": 1703784493, "total_prompt_tokens": 21456674991, "total_native_tokens_reasoning": 0, "num_media_prompt": 379033, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 8451233280, "total_tool_calls": 596142, "requests_with_tool_call_errors": 528 }, "qwen/qwen3-vl-235b-a22b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-235b-a22b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-235b-a22b-instruct", "count": 5690091, "total_completion_tokens": 1299636708, "total_prompt_tokens": 18280770584, "total_native_tokens_reasoning": 21140, "num_media_prompt": 13103591, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1989233920, "total_tool_calls": 44191, "requests_with_tool_call_errors": 29236 }, "deepseek/deepseek-r1-distill-llama-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "deepseek/deepseek-r1-distill-llama-70b", "variant": "standard", "variant_permaslug": "deepseek/deepseek-r1-distill-llama-70b", "count": 634067, "total_completion_tokens": 285712742, "total_prompt_tokens": 1136603945, "total_native_tokens_reasoning": 261923111, "num_media_prompt": 193, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 308541240, "total_tool_calls": 1, "requests_with_tool_call_errors": 0 }, "xiaomi/mimo-v2-flash-20251210:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "xiaomi/mimo-v2-flash-20251210", "variant": "free", "variant_permaslug": "xiaomi/mimo-v2-flash-20251210:free", "count": 83499620, "total_completion_tokens": 92858868926, "total_prompt_tokens": 533854603083, "total_native_tokens_reasoning": 46324822231, "num_media_prompt": 1744, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 140015164033, "total_tool_calls": 2701216, "requests_with_tool_call_errors": 92915 }, "openai/gpt-5-mini-2025-08-07": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-mini-2025-08-07", "variant": "standard", "variant_permaslug": "openai/gpt-5-mini-2025-08-07", "count": 17378914, "total_completion_tokens": 13324307036, "total_prompt_tokens": 88844254326, "total_native_tokens_reasoning": 9028918766, "num_media_prompt": 13994234, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 28117811840, "total_tool_calls": 2659700, "requests_with_tool_call_errors": 18771 }, "qwen/qwen-vl-max-2025-01-25": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-vl-max-2025-01-25", "variant": "standard", "variant_permaslug": "qwen/qwen-vl-max-2025-01-25", "count": 20268, "total_completion_tokens": 4466962, "total_prompt_tokens": 235783583, "total_native_tokens_reasoning": 0, "num_media_prompt": 121122, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 63, "requests_with_tool_call_errors": 21 }, "meta-llama/llama-3.1-405b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.1-405b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.1-405b-instruct", "count": 184805, "total_completion_tokens": 35772350, "total_prompt_tokens": 572213457, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1317, "requests_with_tool_call_errors": 59 }, "aion-labs/aion-rp-llama-3.1-8b": { "date": "2026-01-19 00:00:00", "model_permaslug": "aion-labs/aion-rp-llama-3.1-8b", "variant": "standard", "variant_permaslug": "aion-labs/aion-rp-llama-3.1-8b", "count": 26823, "total_completion_tokens": 4683828, "total_prompt_tokens": 349601833, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5-chat-2025-08-07": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5-chat-2025-08-07", "variant": "standard", "variant_permaslug": "openai/gpt-5-chat-2025-08-07", "count": 2409983, "total_completion_tokens": 550313101, "total_prompt_tokens": 11178088280, "total_native_tokens_reasoning": 0, "num_media_prompt": 369029, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 5831974400, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-4-turbo-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-4-turbo-preview", "variant": "standard", "variant_permaslug": "openai/gpt-4-turbo-preview", "count": 19959, "total_completion_tokens": 3213959, "total_prompt_tokens": 19615720, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 170, "requests_with_tool_call_errors": 0 }, "google/gemma-2-27b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-2-27b-it", "variant": "standard", "variant_permaslug": "google/gemma-2-27b-it", "count": 74530, "total_completion_tokens": 9125901, "total_prompt_tokens": 58902539, "total_native_tokens_reasoning": 0, "num_media_prompt": 175, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-oss-120b:exacto": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-oss-120b", "variant": "exacto", "variant_permaslug": "openai/gpt-oss-120b:exacto", "count": 2692561, "total_completion_tokens": 1828286490, "total_prompt_tokens": 7133026725, "total_native_tokens_reasoning": 927237119, "num_media_prompt": 1, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 572126490, "total_tool_calls": 296243, "requests_with_tool_call_errors": 48531 }, "qwen/qwen3-14b-04-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-14b-04-28", "variant": "standard", "variant_permaslug": "qwen/qwen3-14b-04-28", "count": 2087055, "total_completion_tokens": 1058081808, "total_prompt_tokens": 3127643260, "total_native_tokens_reasoning": 330399419, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1251873947, "total_tool_calls": 54443, "requests_with_tool_call_errors": 1324 }, "meta-llama/llama-3.3-70b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.3-70b-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.3-70b-instruct", "count": 21786809, "total_completion_tokens": 1828166814, "total_prompt_tokens": 22315968072, "total_native_tokens_reasoning": 0, "num_media_prompt": 18, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 6834020500, "total_tool_calls": 304243, "requests_with_tool_call_errors": 160710 }, "arcee-ai/trinity-mini-20251201": { "date": "2026-01-19 00:00:00", "model_permaslug": "arcee-ai/trinity-mini-20251201", "variant": "standard", "variant_permaslug": "arcee-ai/trinity-mini-20251201", "count": 54526, "total_completion_tokens": 51385937, "total_prompt_tokens": 39113112, "total_native_tokens_reasoning": 48019429, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 133, "requests_with_tool_call_errors": 30 }, "qwen/qwen2.5-coder-7b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen2.5-coder-7b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen2.5-coder-7b-instruct", "count": 22439, "total_completion_tokens": 19962041, "total_prompt_tokens": 18486034, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen-2.5-coder-32b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-2.5-coder-32b-instruct", "variant": "standard", "variant_permaslug": "qwen/qwen-2.5-coder-32b-instruct", "count": 570734, "total_completion_tokens": 51384294, "total_prompt_tokens": 726253531, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 170517439, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sourceful/riverflow-v2-standard-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "sourceful/riverflow-v2-standard-preview", "variant": "standard", "variant_permaslug": "sourceful/riverflow-v2-standard-preview", "count": 3311, "total_completion_tokens": 13823425, "total_prompt_tokens": 7310731, "total_native_tokens_reasoning": 0, "num_media_prompt": 2927, "num_media_completion": 3311, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "nousresearch/hermes-3-llama-3.1-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "nousresearch/hermes-3-llama-3.1-70b", "variant": "standard", "variant_permaslug": "nousresearch/hermes-3-llama-3.1-70b", "count": 244353, "total_completion_tokens": 51376380, "total_prompt_tokens": 382266971, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "mistralai/mixtral-8x22b-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mixtral-8x22b-instruct", "variant": "standard", "variant_permaslug": "mistralai/mixtral-8x22b-instruct", "count": 72106, "total_completion_tokens": 13138001, "total_prompt_tokens": 111588907, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 299, "requests_with_tool_call_errors": 37 }, "mistralai/devstral-small-2507": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/devstral-small-2507", "variant": "standard", "variant_permaslug": "mistralai/devstral-small-2507", "count": 594211, "total_completion_tokens": 83734614, "total_prompt_tokens": 2264919430, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 6007, "requests_with_tool_call_errors": 27 }, "mistralai/mistral-7b-instruct-v0.1": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-7b-instruct-v0.1", "variant": "standard", "variant_permaslug": "mistralai/mistral-7b-instruct-v0.1", "count": 39132, "total_completion_tokens": 5984144, "total_prompt_tokens": 9952537, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/o3-mini-high-2025-01-31": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o3-mini-high-2025-01-31", "variant": "standard", "variant_permaslug": "openai/o3-mini-high-2025-01-31", "count": 139048, "total_completion_tokens": 154918975, "total_prompt_tokens": 4333351095, "total_native_tokens_reasoning": 145036096, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 675452544, "total_tool_calls": 233, "requests_with_tool_call_errors": 0 }, "black-forest-labs/flux.2-pro": { "date": "2026-01-19 00:00:00", "model_permaslug": "black-forest-labs/flux.2-pro", "variant": "standard", "variant_permaslug": "black-forest-labs/flux.2-pro", "count": 13472, "total_completion_tokens": 0, "total_prompt_tokens": 2992990, "total_native_tokens_reasoning": 0, "num_media_prompt": 7743, "num_media_completion": 13472, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5.1-codex-max-20251204": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.1-codex-max-20251204", "variant": "standard", "variant_permaslug": "openai/gpt-5.1-codex-max-20251204", "count": 60407, "total_completion_tokens": 44722195, "total_prompt_tokens": 1961313486, "total_native_tokens_reasoning": 25283813, "num_media_prompt": 7886, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1476752384, "total_tool_calls": 38777, "requests_with_tool_call_errors": 201 }, "black-forest-labs/flux.2-flex": { "date": "2026-01-19 00:00:00", "model_permaslug": "black-forest-labs/flux.2-flex", "variant": "standard", "variant_permaslug": "black-forest-labs/flux.2-flex", "count": 1677, "total_completion_tokens": 0, "total_prompt_tokens": 418879, "total_native_tokens_reasoning": 0, "num_media_prompt": 1022, "num_media_completion": 1677, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "google/gemini-2.5-flash-lite-preview-09-2025": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemini-2.5-flash-lite-preview-09-2025", "variant": "standard", "variant_permaslug": "google/gemini-2.5-flash-lite-preview-09-2025", "count": 18586530, "total_completion_tokens": 8480917247, "total_prompt_tokens": 53881010810, "total_native_tokens_reasoning": 1758499158, "num_media_prompt": 6065107, "num_media_completion": 0, "num_audio_prompt": 746913, "total_native_tokens_cached": 14868768460, "total_tool_calls": 358965, "requests_with_tool_call_errors": 3287 }, "mistralai/mistral-small-3.2-24b-instruct-2506": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-small-3.2-24b-instruct-2506", "variant": "standard", "variant_permaslug": "mistralai/mistral-small-3.2-24b-instruct-2506", "count": 5934281, "total_completion_tokens": 3148093352, "total_prompt_tokens": 23268604466, "total_native_tokens_reasoning": 0, "num_media_prompt": 470463, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 4753085600, "total_tool_calls": 87588, "requests_with_tool_call_errors": 13017 }, "black-forest-labs/flux.2-max": { "date": "2026-01-19 00:00:00", "model_permaslug": "black-forest-labs/flux.2-max", "variant": "standard", "variant_permaslug": "black-forest-labs/flux.2-max", "count": 4396, "total_completion_tokens": 0, "total_prompt_tokens": 1235436, "total_native_tokens_reasoning": 0, "num_media_prompt": 3251, "num_media_completion": 4396, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sao10k/l3.1-euryale-70b": { "date": "2026-01-19 00:00:00", "model_permaslug": "sao10k/l3.1-euryale-70b", "variant": "standard", "variant_permaslug": "sao10k/l3.1-euryale-70b", "count": 145937, "total_completion_tokens": 20145246, "total_prompt_tokens": 427655177, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/o4-mini-deep-research-2025-06-26": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/o4-mini-deep-research-2025-06-26", "variant": "standard", "variant_permaslug": "openai/o4-mini-deep-research-2025-06-26", "count": 3748, "total_completion_tokens": 44484465, "total_prompt_tokens": 118312484, "total_native_tokens_reasoning": 40540192, "num_media_prompt": 473, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 2013184, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "aion-labs/aion-1.0": { "date": "2026-01-19 00:00:00", "model_permaslug": "aion-labs/aion-1.0", "variant": "standard", "variant_permaslug": "aion-labs/aion-1.0", "count": 35452, "total_completion_tokens": 68886741, "total_prompt_tokens": 395143297, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sao10k/l3.3-euryale-70b-v2.3": { "date": "2026-01-19 00:00:00", "model_permaslug": "sao10k/l3.3-euryale-70b-v2.3", "variant": "standard", "variant_permaslug": "sao10k/l3.3-euryale-70b-v2.3", "count": 231760, "total_completion_tokens": 22652991, "total_prompt_tokens": 378865067, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "kwaipilot/kat-coder-pro-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "kwaipilot/kat-coder-pro-v1", "variant": "standard", "variant_permaslug": "kwaipilot/kat-coder-pro-v1", "count": 105142, "total_completion_tokens": 46987910, "total_prompt_tokens": 1789650757, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1560217657, "total_tool_calls": 19079, "requests_with_tool_call_errors": 4136 }, "cohere/command-r-08-2024": { "date": "2026-01-19 00:00:00", "model_permaslug": "cohere/command-r-08-2024", "variant": "standard", "variant_permaslug": "cohere/command-r-08-2024", "count": 120705, "total_completion_tokens": 11081999, "total_prompt_tokens": 89475364, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 155, "requests_with_tool_call_errors": 3 }, "liquid/lfm-2.5-1.2b-instruct-20260120:free": { "date": "2026-01-20 00:00:00", "model_permaslug": "liquid/lfm-2.5-1.2b-instruct-20260120", "variant": "free", "variant_permaslug": "liquid/lfm-2.5-1.2b-instruct-20260120:free", "count": 56136, "total_completion_tokens": 9170936, "total_prompt_tokens": 107868868, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "sourceful/riverflow-v2-fast-preview": { "date": "2026-01-19 00:00:00", "model_permaslug": "sourceful/riverflow-v2-fast-preview", "variant": "standard", "variant_permaslug": "sourceful/riverflow-v2-fast-preview", "count": 1820, "total_completion_tokens": 7598500, "total_prompt_tokens": 3182118, "total_native_tokens_reasoning": 0, "num_media_prompt": 1413, "num_media_completion": 1820, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen3-vl-235b-a22b-thinking": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-vl-235b-a22b-thinking", "variant": "standard", "variant_permaslug": "qwen/qwen3-vl-235b-a22b-thinking", "count": 406676, "total_completion_tokens": 1112760537, "total_prompt_tokens": 783612967, "total_native_tokens_reasoning": 938936885, "num_media_prompt": 426919, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 27, "requests_with_tool_call_errors": 3 }, "mistralai/mistral-small-3.1-24b-instruct-2503": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "variant": "standard", "variant_permaslug": "mistralai/mistral-small-3.1-24b-instruct-2503", "count": 682972, "total_completion_tokens": 88256527, "total_prompt_tokens": 824409062, "total_native_tokens_reasoning": 0, "num_media_prompt": 1598, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 55064647, "total_tool_calls": 1, "requests_with_tool_call_errors": 0 }, "stepfun-ai/step3": { "date": "2026-01-19 00:00:00", "model_permaslug": "stepfun-ai/step3", "variant": "standard", "variant_permaslug": "stepfun-ai/step3", "count": 2168, "total_completion_tokens": 3765435, "total_prompt_tokens": 4323362, "total_native_tokens_reasoning": 2620503, "num_media_prompt": 803, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 3, "requests_with_tool_call_errors": 1 }, "z-ai/glm-4.7-flash-20260119": { "date": "2026-01-19 00:00:00", "model_permaslug": "z-ai/glm-4.7-flash-20260119", "variant": "standard", "variant_permaslug": "z-ai/glm-4.7-flash-20260119", "count": 391103, "total_completion_tokens": 503788659, "total_prompt_tokens": 3886937150, "total_native_tokens_reasoning": 385546998, "num_media_prompt": 675, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 938865656, "total_tool_calls": 69581, "requests_with_tool_call_errors": 5346 }, "meta-llama/llama-3.2-11b-vision-instruct": { "date": "2026-01-19 00:00:00", "model_permaslug": "meta-llama/llama-3.2-11b-vision-instruct", "variant": "standard", "variant_permaslug": "meta-llama/llama-3.2-11b-vision-instruct", "count": 783918, "total_completion_tokens": 59546211, "total_prompt_tokens": 3423065046, "total_native_tokens_reasoning": 0, "num_media_prompt": 763954, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "microsoft/phi-4": { "date": "2026-01-19 00:00:00", "model_permaslug": "microsoft/phi-4", "variant": "standard", "variant_permaslug": "microsoft/phi-4", "count": 2800573, "total_completion_tokens": 67183370, "total_prompt_tokens": 807060229, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "anthropic/claude-4.5-opus-20251124": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4.5-opus-20251124", "variant": "standard", "variant_permaslug": "anthropic/claude-4.5-opus-20251124", "count": 10493841, "total_completion_tokens": 6854303978, "total_prompt_tokens": 390764902861, "total_native_tokens_reasoning": 581240085, "num_media_prompt": 10425135, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 239903108464, "total_tool_calls": 5755981, "requests_with_tool_call_errors": 150431 }, "mistralai/ministral-3b-2512": { "date": "2026-01-19 00:00:00", "model_permaslug": "mistralai/ministral-3b-2512", "variant": "standard", "variant_permaslug": "mistralai/ministral-3b-2512", "count": 941810, "total_completion_tokens": 244855602, "total_prompt_tokens": 685990433, "total_native_tokens_reasoning": 0, "num_media_prompt": 8774, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 1098, "requests_with_tool_call_errors": 76 }, "openai/text-embedding-ada-002": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/text-embedding-ada-002", "variant": "standard", "variant_permaslug": "openai/text-embedding-ada-002", "count": 1773891, "total_completion_tokens": 0, "total_prompt_tokens": 2744825472, "total_native_tokens_reasoning": 0, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "openai/gpt-5.1-chat-20251113": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.1-chat-20251113", "variant": "standard", "variant_permaslug": "openai/gpt-5.1-chat-20251113", "count": 516153, "total_completion_tokens": 83117350, "total_prompt_tokens": 2437443388, "total_native_tokens_reasoning": 8020224, "num_media_prompt": 144230, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 947214976, "total_tool_calls": 31605, "requests_with_tool_call_errors": 24 }, "amazon/nova-2-lite-v1": { "date": "2026-01-19 00:00:00", "model_permaslug": "amazon/nova-2-lite-v1", "variant": "standard", "variant_permaslug": "amazon/nova-2-lite-v1", "count": 59703, "total_completion_tokens": 61390805, "total_prompt_tokens": 182561972, "total_native_tokens_reasoning": 10674, "num_media_prompt": 22469, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 5016, "requests_with_tool_call_errors": 5 }, "anthropic/claude-4-opus-20250522": { "date": "2026-01-19 00:00:00", "model_permaslug": "anthropic/claude-4-opus-20250522", "variant": "standard", "variant_permaslug": "anthropic/claude-4-opus-20250522", "count": 99754, "total_completion_tokens": 51593532, "total_prompt_tokens": 1235228141, "total_native_tokens_reasoning": 1243573, "num_media_prompt": 11030, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 520152888, "total_tool_calls": 22752, "requests_with_tool_call_errors": 331 }, "qwen/qwen3-235b-a22b-04-28": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen3-235b-a22b-04-28", "variant": "standard", "variant_permaslug": "qwen/qwen3-235b-a22b-04-28", "count": 664448, "total_completion_tokens": 584861886, "total_prompt_tokens": 1872359913, "total_native_tokens_reasoning": 435221401, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 424807100, "total_tool_calls": 10029, "requests_with_tool_call_errors": 148 }, "openai/gpt-5.2-codex-20260114": { "date": "2026-01-19 00:00:00", "model_permaslug": "openai/gpt-5.2-codex-20260114", "variant": "standard", "variant_permaslug": "openai/gpt-5.2-codex-20260114", "count": 867597, "total_completion_tokens": 976412353, "total_prompt_tokens": 43360971481, "total_native_tokens_reasoning": 651711042, "num_media_prompt": 230805, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 35740070400, "total_tool_calls": 556537, "requests_with_tool_call_errors": 4408 }, "google/gemma-3-12b-it": { "date": "2026-01-19 00:00:00", "model_permaslug": "google/gemma-3-12b-it", "variant": "standard", "variant_permaslug": "google/gemma-3-12b-it", "count": 8397216, "total_completion_tokens": 1393883939, "total_prompt_tokens": 6848742766, "total_native_tokens_reasoning": 0, "num_media_prompt": 746128, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1140641131, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "qwen/qwen-2-vl-7b-instruct:free": { "date": "2026-01-19 00:00:00", "model_permaslug": "qwen/qwen-2-vl-7b-instruct", "variant": "free", "variant_permaslug": "qwen/qwen-2-vl-7b-instruct:free", "count": 51618, "total_completion_tokens": 15733701, "total_prompt_tokens": 160992730, "total_native_tokens_reasoning": 0, "num_media_prompt": 39114, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 0, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 }, "allenai/olmo-3-32b-think-20251121": { "date": "2026-01-20 00:00:00", "model_permaslug": "allenai/olmo-3-32b-think-20251121", "variant": "standard", "variant_permaslug": "allenai/olmo-3-32b-think-20251121", "count": 2, "total_completion_tokens": 1175, "total_prompt_tokens": 1288, "total_native_tokens_reasoning": 1323, "num_media_prompt": 0, "num_media_completion": 0, "num_audio_prompt": 0, "total_native_tokens_cached": 1280, "total_tool_calls": 0, "requests_with_tool_call_errors": 0 } }, "categories": { "x-ai/grok-code-fast-1": [ { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-code-fast-1", "category": "programming", "count": 10836, "total_prompt_tokens": 531133745, "total_completion_tokens": 5665781, "volume": 3.5350348246, "rank": 1 } ], "google/gemini-2.5-flash": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "legal", "count": 7008, "total_prompt_tokens": 38636587, "total_completion_tokens": 1352649, "volume": 13.476538740833334, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "health", "count": 3920, "total_prompt_tokens": 8406078, "total_completion_tokens": 949371, "volume": 3.5860605543, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "academia", "count": 7371, "total_prompt_tokens": 13342756, "total_completion_tokens": 2101928, "volume": 7.608459497666667, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "marketing/seo", "count": 768, "total_prompt_tokens": 3001599, "total_completion_tokens": 369433, "volume": 1.37687878, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "trivia", "count": 1121, "total_prompt_tokens": 1170020, "total_completion_tokens": 82831, "volume": 0.3562632706666667, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "marketing", "count": 2101, "total_prompt_tokens": 6826805, "total_completion_tokens": 945513, "volume": 3.4052504572, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "science", "count": 8539, "total_prompt_tokens": 29778965, "total_completion_tokens": 2507316, "volume": 12.478750967766667, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "roleplay", "count": 13043, "total_prompt_tokens": 80049644, "total_completion_tokens": 4300091, "volume": 25.597364748133334, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "finance", "count": 4283, "total_prompt_tokens": 13330084, "total_completion_tokens": 1235691, "volume": 4.560706761466666, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "technology", "count": 15530, "total_prompt_tokens": 49818555, "total_completion_tokens": 3253293, "volume": 17.849434636999998, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash", "category": "translation", "count": 5708, "total_prompt_tokens": 8180159, "total_completion_tokens": 818147, "volume": 3.362067071, "rank": 6 } ], "openai/gpt-oss-120b": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "translation", "count": 43949, "total_prompt_tokens": 46903567, "total_completion_tokens": 15150366, "volume": 1.29545287424, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "trivia", "count": 744, "total_prompt_tokens": 1635428, "total_completion_tokens": 370527, "volume": 0.0520163832, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "finance", "count": 2467, "total_prompt_tokens": 17372657, "total_completion_tokens": 1564553, "volume": 3.40829904244, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "legal", "count": 2180, "total_prompt_tokens": 14313450, "total_completion_tokens": 803310, "volume": 2.0643605301999997, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "marketing", "count": 1416, "total_prompt_tokens": 9217422, "total_completion_tokens": 1435333, "volume": 0.42303750005, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "academia", "count": 10785, "total_prompt_tokens": 7751331, "total_completion_tokens": 2010781, "volume": 0.65319241523, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "science", "count": 3714, "total_prompt_tokens": 19163898, "total_completion_tokens": 2395485, "volume": 3.55779855165, "rank": 8 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-120b", "category": "technology", "count": 6058, "total_prompt_tokens": 35136008, "total_completion_tokens": 4671065, "volume": 5.57806890951, "rank": 9 } ], "google/gemini-3-flash-preview-20251217": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "health", "count": 3124, "total_prompt_tokens": 11738693, "total_completion_tokens": 1832928, "volume": 10.594289208500001, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "finance", "count": 3791, "total_prompt_tokens": 22809969, "total_completion_tokens": 1140177, "volume": 9.9780890215, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "technology", "count": 13378, "total_prompt_tokens": 119941389, "total_completion_tokens": 4115561, "volume": 52.79453034583333, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "programming", "count": 9684, "total_prompt_tokens": 244232887, "total_completion_tokens": 3362604, "volume": 34.280786395, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "academia", "count": 4949, "total_prompt_tokens": 10603509, "total_completion_tokens": 3881727, "volume": 18.143410949, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "science", "count": 6993, "total_prompt_tokens": 46459659, "total_completion_tokens": 2309513, "volume": 26.611923623166668, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "legal", "count": 2161, "total_prompt_tokens": 5267428, "total_completion_tokens": 540977, "volume": 4.59874074, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "trivia", "count": 602, "total_prompt_tokens": 1061500, "total_completion_tokens": 112671, "volume": 0.74280744, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "translation", "count": 6648, "total_prompt_tokens": 10962479, "total_completion_tokens": 1464967, "volume": 7.920350073, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "marketing", "count": 1177, "total_prompt_tokens": 3392588, "total_completion_tokens": 331680, "volume": 2.0894731898333334, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-flash-preview-20251217", "category": "roleplay", "count": 7599, "total_prompt_tokens": 56120704, "total_completion_tokens": 2970028, "volume": 26.75196715066667, "rank": 8 } ], "x-ai/grok-4.1-fast": [ { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "trivia", "count": 1015, "total_prompt_tokens": 1891019, "total_completion_tokens": 237321, "volume": 0.691084712, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "roleplay", "count": 11716, "total_prompt_tokens": 93141347, "total_completion_tokens": 4738511, "volume": 11.2644881925, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "marketing", "count": 1137, "total_prompt_tokens": 5695128, "total_completion_tokens": 787523, "volume": 1.842000172, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "science", "count": 5103, "total_prompt_tokens": 25233712, "total_completion_tokens": 1614711, "volume": 5.229664069, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "technology", "count": 5860, "total_prompt_tokens": 45123767, "total_completion_tokens": 2051482, "volume": 9.6054095765, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "health", "count": 433, "total_prompt_tokens": 3899145, "total_completion_tokens": 346844, "volume": 1.158146058, "rank": 8 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "legal", "count": 392, "total_prompt_tokens": 3200474, "total_completion_tokens": 209423, "volume": 0.922147195, "rank": 9 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "finance", "count": 2190, "total_prompt_tokens": 11119589, "total_completion_tokens": 758446, "volume": 4.3694143875, "rank": 9 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4.1-fast", "category": "translation", "count": 1797, "total_prompt_tokens": 2182858, "total_completion_tokens": 465645, "volume": 0.813118916, "rank": 9 } ], "xiaomi/mimo-v2-flash-20251210:free": [ { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "marketing", "count": 1272, "total_prompt_tokens": 66919804, "total_completion_tokens": 585052, "volume": 0, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "academia", "count": 4181, "total_prompt_tokens": 10009895, "total_completion_tokens": 32336029, "volume": 0.1, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "science", "count": 24083, "total_prompt_tokens": 114486859, "total_completion_tokens": 53325428, "volume": 0.06, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "technology", "count": 15335, "total_prompt_tokens": 169831265, "total_completion_tokens": 12225969, "volume": 0.1, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "roleplay", "count": 11866, "total_prompt_tokens": 147487589, "total_completion_tokens": 8563346, "volume": 0.1, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "marketing/seo", "count": 2090, "total_prompt_tokens": 5320314, "total_completion_tokens": 3194864, "volume": 0, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "legal", "count": 773, "total_prompt_tokens": 5020299, "total_completion_tokens": 1662541, "volume": 0, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "finance", "count": 2717, "total_prompt_tokens": 15341092, "total_completion_tokens": 1247697, "volume": 0.12, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "programming", "count": 20036, "total_prompt_tokens": 129182027, "total_completion_tokens": 14373249, "volume": 0.08, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "xiaomi/mimo-v2-flash-20251210:free", "category": "translation", "count": 2337, "total_prompt_tokens": 3678570, "total_completion_tokens": 2361201, "volume": 0, "rank": 7 } ], "deepseek/deepseek-v3.2-20251201": [ { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-v3.2-20251201", "category": "roleplay", "count": 27446, "total_prompt_tokens": 345459113, "total_completion_tokens": 12965361, "volume": 33.532336778310004, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-v3.2-20251201", "category": "academia", "count": 1325, "total_prompt_tokens": 7576854, "total_completion_tokens": 2135178, "volume": 2.64958215181, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-v3.2-20251201", "category": "programming", "count": 5521, "total_prompt_tokens": 72255007, "total_completion_tokens": 3243899, "volume": 17.03625339718, "rank": 9 } ], "anthropic/claude-4.5-sonnet-20250929": [ { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "technology", "count": 6664, "total_prompt_tokens": 352763361, "total_completion_tokens": 2402697, "volume": 227.956396639, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "programming", "count": 6564, "total_prompt_tokens": 293890452, "total_completion_tokens": 3101214, "volume": 442.8547804285, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "science", "count": 2134, "total_prompt_tokens": 62510757, "total_completion_tokens": 855040, "volume": 139.5991539595, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "health", "count": 467, "total_prompt_tokens": 5607919, "total_completion_tokens": 222504, "volume": 24.1709653185, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "marketing", "count": 187, "total_prompt_tokens": 2971866, "total_completion_tokens": 96519, "volume": 11.1058761635, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "academia", "count": 737, "total_prompt_tokens": 6184279, "total_completion_tokens": 335053, "volume": 23.17357555, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-sonnet-20250929", "category": "marketing/seo", "count": 324, "total_prompt_tokens": 883787, "total_completion_tokens": 84515, "volume": 4.4639487, "rank": 10 } ], "x-ai/grok-4-fast": [ { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4-fast", "category": "marketing/seo", "count": 3379, "total_prompt_tokens": 14025501, "total_completion_tokens": 4645751, "volume": 7.4791038835000005, "rank": 1 }, { "id": 0, "date": "2026-01-25", "model": "x-ai/grok-4-fast", "category": "legal", "count": 70, "total_prompt_tokens": 4384559, "total_completion_tokens": 97836, "volume": 1.7034889340000001, "rank": 7 } ], "meta-llama/llama-3.1-8b-instruct": [ { "id": 0, "date": "2026-01-25", "model": "meta-llama/llama-3.1-8b-instruct", "category": "translation", "count": 11865, "total_prompt_tokens": 13137000, "total_completion_tokens": 669287, "volume": 0.8780004331, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "meta-llama/llama-3.1-8b-instruct", "category": "trivia", "count": 1804, "total_prompt_tokens": 639350, "total_completion_tokens": 6200, "volume": 0.018702475, "rank": 7 } ], "google/gemini-2.5-flash-lite": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "marketing", "count": 5138, "total_prompt_tokens": 19811003, "total_completion_tokens": 1550916, "volume": 1.294499445, "rank": 2 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "technology", "count": 15532, "total_prompt_tokens": 86937346, "total_completion_tokens": 8144806, "volume": 4.953564093433333, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "translation", "count": 9568, "total_prompt_tokens": 9797985, "total_completion_tokens": 2853191, "volume": 1.96591817301, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "legal", "count": 1631, "total_prompt_tokens": 4395949, "total_completion_tokens": 435010, "volume": 0.724170027, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "health", "count": 3795, "total_prompt_tokens": 3335379, "total_completion_tokens": 1003887, "volume": 0.8050978128, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "academia", "count": 1612, "total_prompt_tokens": 3753502, "total_completion_tokens": 1173738, "volume": 0.9613857419, "rank": 8 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "marketing/seo", "count": 543, "total_prompt_tokens": 909103, "total_completion_tokens": 94926, "volume": 0.1285888524, "rank": 9 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "science", "count": 7270, "total_prompt_tokens": 13589676, "total_completion_tokens": 2063695, "volume": 2.110919856, "rank": 9 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "trivia", "count": 543, "total_prompt_tokens": 531346, "total_completion_tokens": 53508, "volume": 0.0630259303, "rank": 10 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "finance", "count": 5482, "total_prompt_tokens": 7165441, "total_completion_tokens": 638545, "volume": 1.0517388072, "rank": 10 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite", "category": "roleplay", "count": 21035, "total_prompt_tokens": 48354219, "total_completion_tokens": 1130199, "volume": 4.3890588916999995, "rank": 10 } ], "openai/gpt-4o-mini": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4o-mini", "category": "finance", "count": 2223, "total_prompt_tokens": 16924600, "total_completion_tokens": 306443, "volume": 2.780786855, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4o-mini", "category": "trivia", "count": 1433, "total_prompt_tokens": 1543771, "total_completion_tokens": 16635, "volume": 0.17132043900000002, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4o-mini", "category": "science", "count": 5641, "total_prompt_tokens": 23735619, "total_completion_tokens": 704597, "volume": 4.037689341, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4o-mini", "category": "translation", "count": 9736, "total_prompt_tokens": 2746528, "total_completion_tokens": 475198, "volume": 0.6885863495, "rank": 8 } ], "google/gemini-2.0-flash-001": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.0-flash-001", "category": "translation", "count": 22926, "total_prompt_tokens": 11087168, "total_completion_tokens": 1622898, "volume": 1.862434215, "rank": 3 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.0-flash-001", "category": "academia", "count": 2513, "total_prompt_tokens": 7466194, "total_completion_tokens": 1841887, "volume": 1.342845945, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.0-flash-001", "category": "trivia", "count": 516, "total_prompt_tokens": 665320, "total_completion_tokens": 57882, "volume": 0.113648232, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.0-flash-001", "category": "roleplay", "count": 67719, "total_prompt_tokens": 43658450, "total_completion_tokens": 7086464, "volume": 7.0095375933333335, "rank": 9 } ], "tngtech/deepseek-r1t2-chimera:free": [ { "id": 0, "date": "2026-01-25", "model": "tngtech/deepseek-r1t2-chimera:free", "category": "roleplay", "count": 9190, "total_prompt_tokens": 95442040, "total_completion_tokens": 7646977, "volume": 0.12, "rank": 3 } ], "anthropic/claude-4.5-haiku-20251001": [ { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-haiku-20251001", "category": "health", "count": 262, "total_prompt_tokens": 4557388, "total_completion_tokens": 215336, "volume": 6.7674549299999995, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-haiku-20251001", "category": "science", "count": 1066, "total_prompt_tokens": 13496493, "total_completion_tokens": 450995, "volume": 13.7007391425, "rank": 10 } ], "anthropic/claude-4.5-opus-20251124": [ { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-opus-20251124", "category": "programming", "count": 5210, "total_prompt_tokens": 228257655, "total_completion_tokens": 2318898, "volume": 497.071782615, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-opus-20251124", "category": "science", "count": 1324, "total_prompt_tokens": 30815590, "total_completion_tokens": 649554, "volume": 92.5945990625, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4.5-opus-20251124", "category": "technology", "count": 3258, "total_prompt_tokens": 92579477, "total_completion_tokens": 1201066, "volume": 280.19274504, "rank": 5 } ], "openai/gpt-4.1-nano-2025-04-14": [ { "id": 0, "date": "2026-01-24", "model": "openai/gpt-4.1-nano-2025-04-14", "category": "marketing/seo", "count": 908, "total_prompt_tokens": 2155843, "total_completion_tokens": 961508, "volume": 0.51574823, "rank": 4 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4.1-nano-2025-04-14", "category": "finance", "count": 1959, "total_prompt_tokens": 12503739, "total_completion_tokens": 86411, "volume": 0.596097646, "rank": 8 } ], "openai/gpt-5-mini-2025-08-07": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-5-mini-2025-08-07", "category": "finance", "count": 2817, "total_prompt_tokens": 15176992, "total_completion_tokens": 1237641, "volume": 7.2602494455, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-5-mini-2025-08-07", "category": "marketing/seo", "count": 525, "total_prompt_tokens": 1106759, "total_completion_tokens": 279745, "volume": 1.41557525, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-5-mini-2025-08-07", "category": "technology", "count": 3278, "total_prompt_tokens": 40591099, "total_completion_tokens": 1601342, "volume": 12.391080005000001, "rank": 8 } ], "deepseek/deepseek-chat-v3-0324": [ { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-chat-v3-0324", "category": "health", "count": 558, "total_prompt_tokens": 4308758, "total_completion_tokens": 299797, "volume": 1.3899661247, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-chat-v3-0324", "category": "roleplay", "count": 14708, "total_prompt_tokens": 79061746, "total_completion_tokens": 3325115, "volume": 26.21701005124, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-chat-v3-0324", "category": "trivia", "count": 403, "total_prompt_tokens": 555811, "total_completion_tokens": 38385, "volume": 0.1966826763, "rank": 9 } ], "google/gemini-2.5-flash-lite-preview-09-2025": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "category": "legal", "count": 1076, "total_prompt_tokens": 5233542, "total_completion_tokens": 140817, "volume": 0.535424877, "rank": 5 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "category": "health", "count": 2233, "total_prompt_tokens": 3815757, "total_completion_tokens": 424381, "volume": 0.5059171771000001, "rank": 9 } ], "mistralai/mistral-small-24b-instruct-2501": [ { "id": 0, "date": "2026-01-25", "model": "mistralai/mistral-small-24b-instruct-2501", "category": "marketing/seo", "count": 3227, "total_prompt_tokens": 1646000, "total_completion_tokens": 153600, "volume": 0.15526883, "rank": 5 } ], "anthropic/claude-4-sonnet-20250522": [ { "id": 0, "date": "2026-01-25", "model": "anthropic/claude-4-sonnet-20250522", "category": "health", "count": 1008, "total_prompt_tokens": 3654025, "total_completion_tokens": 897830, "volume": 28.639203039999998, "rank": 6 } ], "openai/gpt-4.1-mini-2025-04-14": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4.1-mini-2025-04-14", "category": "marketing/seo", "count": 177, "total_prompt_tokens": 1637555, "total_completion_tokens": 56395, "volume": 0.46711184399999994, "rank": 6 }, { "id": 0, "date": "2026-01-25", "model": "openai/gpt-4.1-mini-2025-04-14", "category": "translation", "count": 4681, "total_prompt_tokens": 1943692, "total_completion_tokens": 432633, "volume": 1.446540652, "rank": 10 } ], "mistralai/devstral-2512:free": [ { "id": 0, "date": "2026-01-25", "model": "mistralai/devstral-2512:free", "category": "programming", "count": 2916, "total_prompt_tokens": 119421491, "total_completion_tokens": 1476345, "volume": 0.06, "rank": 6 } ], "minimax/minimax-m2.1": [ { "id": 0, "date": "2026-01-25", "model": "minimax/minimax-m2.1", "category": "programming", "count": 2277, "total_prompt_tokens": 103670532, "total_completion_tokens": 1221384, "volume": 5.0084127714, "rank": 7 } ], "deepseek/deepseek-chat-v3.1": [ { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-chat-v3.1", "category": "roleplay", "count": 14823, "total_prompt_tokens": 61299217, "total_completion_tokens": 1521221, "volume": 17.4936888335, "rank": 7 }, { "id": 0, "date": "2026-01-25", "model": "deepseek/deepseek-chat-v3.1", "category": "finance", "count": 697, "total_prompt_tokens": 12385381, "total_completion_tokens": 1316875, "volume": 3.709949474, "rank": 7 } ], "openai/gpt-5.1-20251113": [ { "id": 0, "date": "2026-01-24", "model": "openai/gpt-5.1-20251113", "category": "marketing/seo", "count": 31, "total_prompt_tokens": 1101866, "total_completion_tokens": 22637, "volume": 1.6054705, "rank": 8 } ], "google/gemma-3-12b-it": [ { "id": 0, "date": "2026-01-25", "model": "google/gemma-3-12b-it", "category": "legal", "count": 733, "total_prompt_tokens": 3536254, "total_completion_tokens": 764721, "volume": 0.42422915879999995, "rank": 8 } ], "z-ai/glm-4.6": [ { "id": 0, "date": "2026-01-25", "model": "z-ai/glm-4.6", "category": "trivia", "count": 32, "total_prompt_tokens": 611200, "total_completion_tokens": 2650, "volume": 0.094958016, "rank": 8 } ], "z-ai/glm-4.7-20251222": [ { "id": 0, "date": "2026-01-25", "model": "z-ai/glm-4.7-20251222", "category": "programming", "count": 3469, "total_prompt_tokens": 93287542, "total_completion_tokens": 3634332, "volume": 48.25153520348, "rank": 8 }, { "id": 0, "date": "2026-01-25", "model": "z-ai/glm-4.7-20251222", "category": "technology", "count": 1401, "total_prompt_tokens": 36004408, "total_completion_tokens": 1451833, "volume": 23.15973101437, "rank": 10 } ], "qwen/qwen3-30b-a3b-04-28": [ { "id": 0, "date": "2026-01-25", "model": "qwen/qwen3-30b-a3b-04-28", "category": "marketing", "count": 948, "total_prompt_tokens": 2102350, "total_completion_tokens": 726050, "volume": 0.48477359, "rank": 8 } ], "google/gemini-3-pro-preview-20251117": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-pro-preview-20251117", "category": "marketing", "count": 77, "total_prompt_tokens": 2226575, "total_completion_tokens": 87360, "volume": 4.43219952, "rank": 9 }, { "id": 0, "date": "2026-01-25", "model": "google/gemini-3-pro-preview-20251117", "category": "programming", "count": 2091, "total_prompt_tokens": 60974690, "total_completion_tokens": 2248711, "volume": 95.426867561, "rank": 10 } ], "openai/gpt-5.2-20251211": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-5.2-20251211", "category": "academia", "count": 1625, "total_prompt_tokens": 4304664, "total_completion_tokens": 351223, "volume": 16.587270996, "rank": 9 } ], "google/gemini-2.5-pro": [ { "id": 0, "date": "2026-01-25", "model": "google/gemini-2.5-pro", "category": "academia", "count": 342, "total_prompt_tokens": 3960607, "total_completion_tokens": 673794, "volume": 14.30496995, "rank": 10 } ], "openai/gpt-oss-20b": [ { "id": 0, "date": "2026-01-25", "model": "openai/gpt-oss-20b", "category": "marketing", "count": 220, "total_prompt_tokens": 1838140, "total_completion_tokens": 209244, "volume": 0.13806193565, "rank": 10 } ], "qwen/qwen3-embedding-8b": [ { "id": 0, "date": "2026-01-25", "model": "qwen/qwen3-embedding-8b", "category": "legal", "count": 233, "total_prompt_tokens": 2744490, "total_completion_tokens": 0, "volume": 0.03424931, "rank": 10 } ], "meta-llama/llama-3-8b-instruct": [ { "id": 0, "date": "2026-01-25", "model": "meta-llama/llama-3-8b-instruct", "category": "health", "count": 908, "total_prompt_tokens": 3823250, "total_completion_tokens": 9200, "volume": 0.02727106, "rank": 10 } ] } }