{"data":[{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Claude Opus 5 是Anthropic 针对高要求推理、编码及长期目标代理工作的旗舰模型。该模型在端到端软件任务、代码审查与缺陷检测、图表与文档的视觉分析、复杂办公交付物处理以及并行子代理协调方面表现尤为突出。该模型在处理复杂任务时依然保持出色的指令遵循和工具使用能力，同时在低资源设置下也能高效应对以延迟和token效率为核心的负载需求。","context_length":1000000,"created":1784851200,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents. The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","developer":"knox","id":"anthropic/claude-opus-5","is_provider_model":true,"last_updated":1784931619,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Opus 5","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"25.00","image":"","input_cache_read":"0.50","input_cache_write":"6.25","prompt":"5.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-07-24","root":"anthropic/claude-opus-5","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1784592000,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","developer":"google","id":"google/gemini-3.6-flash","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 3.6 Flash","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000075","image":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.00000008333333333333334","prompt":"0.0000015","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-21","root":"google/gemini-3.6-flash","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":"Kimi K3 是 Moonshot AI 开发的一款 2.8T 参数的开放权重多模态推理模型。它适用于复杂的编码、知识工作和长期智能体工作流，尤其擅长处理大型代码库、使用工具、调试以及基于图像、日志、测试和运行时反馈进行迭代。其架构采用 KDA 和注意力残差来提高计算效率。","context_length":1048576,"created":1784160000,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","developer":"moonshotai","id":"moonshotai/kimi-k3","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"MoonshotAI: Kimi K3","object":"model","owned_by":"moonshotai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.0000003","input_cache_write":null,"prompt":"0.000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-16","root":"moonshotai/kimi-k3","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","developer":"openai","id":"openai/gpt-5.6-terra-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Terra Pro","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.00000025","input_cache_write":"0.000003125","prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-terra-pro","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","developer":"openai","id":"openai/gpt-5.6-sol","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Sol","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00003","image":null,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-sol","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","developer":"openai","id":"openai/gpt-5.6-luna-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Luna Pro","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-luna-pro","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","developer":"openai","id":"openai/gpt-5.6-terra","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Terra","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.00000025","input_cache_write":"0.000003125","prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-terra","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","developer":"openai","id":"openai/gpt-5.6-sol-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Sol Pro","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00003","image":null,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-sol-pro","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1783555200,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","developer":"openai","id":"openai/gpt-5.6-luna","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.6 Luna","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-luna","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":500000,"created":1783468800,"description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","developer":"x-ai","id":"x-ai/grok-4.5","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"xAI: Grok 4.5","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":"0.0000005","input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-07-08","root":"x-ai/grok-4.5","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Claude Fable 5 是 Anthropic 公司推出的 Mythos 级模型，专为自主知识工作和编码而设计。它支持文本、图像和文件输入，并输出文本，具备推理能力，上下文窗口大小可达 100 万个标记。适用于以往需要频繁人工干预的长时间运行、复杂且异步的任务。尤其擅长处理原本需要人工耗费数小时、数天甚至数周才能完成的端到端工作，能够应对长时间运行、含义模糊或高度多步骤的问题。能够以极低的错误率执行范围明确的任务，通过验证循环自动纠正错误，并配备了强大的安全保障机制。","context_length":1000000,"created":1782864000,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","developer":"knox","id":"anthropic/claude-fable-5","is_provider_model":true,"last_updated":1784931619,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Fable 5","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"50.00","image":"","input_cache_read":"1.25","input_cache_write":"12.50","prompt":"10.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-07-01","root":"anthropic/claude-fable-5","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Sonnet 5 是 Anthropic 公司功能最强大的 Sonnet 系列模型，在编码、智能体和专业工作方面均展现出卓越的性能。它支持自适应思维，并提供多种推理难度级别（低、中、高、最高和超高）、100 万个词元的上下文窗口，以及文本、图像和文件输入。Sonnet 5 采用更新的词法分析器，并包含实时网络安全防护措施，可阻止某些高风险的双重用途活动。","context_length":1000000,"created":1782864000,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","developer":"knox","id":"anthropic/claude-sonnet-5","is_provider_model":true,"last_updated":1784931619,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Sonnet 5","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"10.00","image":"","input_cache_read":"0.20","input_cache_write":"2.50","prompt":"2.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-07-01","root":"anthropic/claude-sonnet-5","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":131072,"created":1781740800,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","developer":"google","id":"google/gemini-3.1-flash-image","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.0000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-06-18","root":"google/gemini-3.1-flash-image","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":65536,"created":1781740800,"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...","developer":"google","id":"google/gemini-3-pro-image","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-06-18","root":"google/gemini-3-pro-image","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1781568000,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","developer":"z-ai","id":"z-ai/glm-5.2","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Z.ai: GLM 5.2","object":"model","owned_by":"z-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000044","image":null,"input_cache_read":"0.00000026","input_cache_write":null,"prompt":"0.0000014","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-06-16","root":"z-ai/glm-5.2","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"GPT Image 2 是 OpenAI 最先进的图片生成模型，可快速生成和编辑高质量图片。支持灵活的图片尺寸和高保真度图像输入。","context_length":131072,"created":1781049600,"description":"GPT Image 2 is OpenAI's state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs.","developer":"knox","id":"gpt-image-2","is_provider_model":true,"last_updated":1781065739,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"GPT Image 2","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"30.00","image":"8.00","input_cache_read":"2.00","input_cache_write":"4.00","prompt":"8.00","web_search":""},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-10","root":"gpt-image-2","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":131000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Opus 4.8 是 Opus 4.7 的重点升级，是 Anthropic 用于编码、代理任务和企业工作流程的最佳通用模型。它建立在以前 Opus 模型的优势之上，在复杂的多步骤编码任务上具有更强的性能。 Anthropic 建议将其用于长期编码和代理任务。它在专业工作方面也更强，包括文件起草、数据分析和演示。","context_length":1000000,"created":1780358400,"description":"Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic's best generally available model for coding, agentic tasks, and enterprise workflows. It builds on the strengths of previous Opus models with stronger performance on complex, multi-step coding tasks. Anthropic recommends using it on long-horizon coding and agentic tasks. It is also stronger on professional work, including document drafting, data analysis, and presentations.","developer":"knox","id":"anthropic/claude-opus-4.8","is_provider_model":true,"last_updated":1784931619,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Opus 4.8","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"25.00","image":"","input_cache_read":"0.50","input_cache_write":"6.25","prompt":"5.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-02","root":"anthropic/claude-opus-4.8","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Claude Sonnet 4.6 是迄今为止功能最强大的 Sonnet 系列模型，在编码、代理和专业工作方面均展现出卓越的性能。它尤其擅长迭代开发、复杂代码库导航、端到端项目管理（含内存管理）、文档创建以及在 Web 质量保证和工作流自动化方面的出色计算机应用。","context_length":1000000,"created":1780358400,"description":"Claude Sonnet 4.6 is the most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","developer":"knox","id":"anthropic/claude-sonnet-4.6","is_provider_model":true,"last_updated":1784931619,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Sonnet 4.6","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"15.00","image":"","input_cache_read":"0.30","input_cache_write":"3.75","prompt":"3.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-02","root":"anthropic/claude-sonnet-4.6","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1780185600,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","developer":"minimax","id":"minimax/minimax-m3","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"MiniMax: MiniMax M3","object":"model","owned_by":"minimax","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000012","image":null,"input_cache_read":"0.00000006","input_cache_write":null,"prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-31","root":"minimax/minimax-m3","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":256000,"created":1779926400,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","developer":"stepfun","id":"stepfun/step-3.7-flash","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"StepFun: Step 3.7 Flash","object":"model","owned_by":"stepfun","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000115","image":null,"input_cache_read":"0.00000004","input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-28","root":"stepfun/step-3.7-flash","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tools","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":256000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"chinese_description":null,"context_length":1000000,"created":1779840000,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","developer":"anthropic","id":"anthropic/claude-opus-4.8-fast","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","object":"model","owned_by":"anthropic","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00005","image":null,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-27","root":"anthropic/claude-opus-4.8-fast","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"chinese_description":null,"context_length":1000000,"created":1779321600,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","developer":"qwen","id":"qwen/qwen3.7-max","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Qwen: Qwen3.7 Max","object":"model","owned_by":"qwen","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000075","image":null,"input_cache_read":null,"input_cache_write":"0.000003125","prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-21","root":"qwen/qwen3.7-max","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1779148800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","developer":"google","id":"google/gemini-3.5-flash","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 3.5 Flash","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000009","image":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.00000008333333333333334","prompt":"0.0000015","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-19","root":"google/gemini-3.5-flash","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1778112000,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","developer":"google","id":"google/gemini-3.1-flash-lite","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 3.1 Flash Lite","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.00000008333333333333334","prompt":"0.00000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-07","root":"google/gemini-3.1-flash-lite","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":1000000,"created":1777507200,"description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","developer":"x-ai","id":"x-ai/grok-4.3","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"xAI: Grok 4.3","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.00000125","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-30","root":"x-ai/grok-4.3","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1776988800,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","developer":"openai","id":"openai/gpt-5.5","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.5","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00003","image":null,"input_cache_read":"0.0000005","input_cache_write":null,"prompt":"0.000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"openai/gpt-5.5","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":1048576,"created":1776988800,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","developer":"deepseek","id":"deepseek/deepseek-v4-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"DeepSeek: DeepSeek V4 Pro","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000087","image":null,"input_cache_read":"0.00000003625","input_cache_write":null,"prompt":"0.000000435","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"deepseek/deepseek-v4-pro","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":384000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":1048576,"created":1776988800,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","developer":"deepseek","id":"deepseek/deepseek-v4-flash","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"DeepSeek: DeepSeek V4 Flash","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000028","image":null,"input_cache_read":"0.000000028","input_cache_write":null,"prompt":"0.00000014","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"deepseek/deepseek-v4-flash","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":384000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1776816000,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","developer":"xiaomi","id":"xiaomi/mimo-v2.5-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Xiaomi: MiMo-V2.5-Pro","object":"model","owned_by":"xiaomi","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-22","root":"xiaomi/mimo-v2.5-pro","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["image","text","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"chinese_description":null,"context_length":262144,"created":1775088000,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","developer":"google","id":"google/gemma-4-31b-it","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemma 4 31B","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000038","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000013","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-02","root":"google/gemma-4-31b-it","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":400000,"created":1773705600,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","developer":"openai","id":"openai/gpt-5.4-mini","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.4 Mini","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000045","image":null,"input_cache_read":"0.000000075","input_cache_write":null,"prompt":"0.00000075","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-17","root":"openai/gpt-5.4-mini","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":262144,"created":1773187200,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","developer":"nvidia","id":"nvidia/nemotron-3-super-120b-a12b","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"NVIDIA: Nemotron 3 Super","object":"model","owned_by":"nvidia","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000045","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000009","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-11","root":"nvidia/nemotron-3-super-120b-a12b","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1772668800,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","developer":"openai","id":"openai/gpt-5.4","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.4","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.00000025","input_cache_write":null,"prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-05","root":"openai/gpt-5.4","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":128000,"created":1772496000,"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...","developer":"openai","id":"openai/gpt-5.3-chat","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.3 Chat","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000014","image":null,"input_cache_read":"0.000000175","input_cache_write":null,"prompt":"0.00000175","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-03","root":"openai/gpt-5.3-chat","source":"openrouter","supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":400000,"created":1771891200,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","developer":"openai","id":"openai/gpt-5.3-codex","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"OpenAI: GPT-5.3-Codex","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000014","image":null,"input_cache_read":"0.000000175","input_cache_write":null,"prompt":"0.00000175","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-02-24","root":"openai/gpt-5.3-codex","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["audio","file","image","text","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1771459200,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","developer":"google","id":"google/gemini-3.1-pro-preview","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 3.1 Pro Preview","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-02-19","root":"google/gemini-3.1-pro-preview","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"chinese_description":null,"context_length":-1,"created":1767225600,"description":"Knox Memory System - AI model with unlimited context length through intelligent memory management. Orchestrates multiple underlying models via Plan-Task-Memory architecture.","developer":"knox","id":"knox/knox-ms","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Knox-MS","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"-1","image":"-1","input_cache_read":"0","input_cache_write":"0","prompt":"-1","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-01-01","root":"knox/knox-ms","source":"openrouter","supported_parameters":["enable_vector_search","include_reasoning","max_tokens","memory_mode","project_id","reasoning","rerank_threshold","response_format","session_id","stop","structured_outputs","temperature","tool_choice","tools","top_k","vector_top_k","verbosity"],"top_provider":{"context_length":-1,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":262144,"created":1765238400,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","developer":"mistralai","id":"mistralai/devstral-2512","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Mistral: Devstral 2 2512","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000002","image":null,"input_cache_read":"0.00000004","input_cache_write":null,"prompt":"0.0000004","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-09","root":"mistralai/devstral-2512","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":131072,"created":1764547200,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","developer":"deepseek","id":"deepseek/deepseek-v3.2","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"DeepSeek: DeepSeek V3.2","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000003432","image":null,"input_cache_read":"0.00000002288","input_cache_write":null,"prompt":"0.0000002288","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-01","root":"deepseek/deepseek-v3.2","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":262144,"created":1764547200,"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.","developer":"mistralai","id":"mistralai/mistral-large-2512","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Mistral: Mistral Large 3 2512","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":null,"input_cache_read":"0.00000005","input_cache_write":null,"prompt":"0.0000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-01","root":"mistralai/mistral-large-2512","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":200000,"created":1761782400,"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...","developer":"perplexity","id":"perplexity/sonar-pro-search","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Perplexity: Sonar Pro Search","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-30","root":"perplexity/sonar-pro-search","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"chinese_description":"Claude Haiku 4.5是Anthropic公司最快、最高效的模型，以远低于大型Claude模型的成本和延迟，提供接近前沿的智能水平。在推理、编码和计算机使用任务上与Claude Sonnet 4性能相当，Haiku 4.5将前沿级能力应用于实时及高并发场景。","context_length":200000,"created":1760486400,"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.","developer":"anthropic","id":"anthropic/claude-haiku-4.5","is_provider_model":false,"last_updated":1784932022,"logo_url":null,"name":"Anthropic: Claude Haiku 4.5","object":"model","owned_by":"anthropic","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000005","image":null,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-15","root":"anthropic/claude-haiku-4.5","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":32768,"created":1759795200,"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,...","developer":"google","id":"google/gemini-2.5-flash-image","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-07","root":"google/gemini-2.5-flash-image","source":"openrouter","supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":256000,"created":1756166400,"description":"Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...","developer":"x-ai","id":"x-ai/grok-code-fast-1","is_provider_model":false,"last_updated":1777835764,"logo_url":null,"name":"xAI: Grok Code Fast 1","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":null,"input_cache_read":"0.00000002","input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-26","root":"x-ai/grok-code-fast-1","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":10000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":256000,"created":1754006400,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","developer":"mistralai","id":"mistralai/codestral-2508","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Mistral: Codestral 2508","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000009","image":null,"input_cache_read":"0.00000003","input_cache_write":null,"prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-01","root":"mistralai/codestral-2508","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","file","audio","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1750118400,"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...","developer":"google","id":"google/gemini-2.5-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 2.5 Pro","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00001","image":"0.00000125","input_cache_read":"0.000000125","input_cache_write":"0.000000375","prompt":"0.00000125","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-06-17","root":"google/gemini-2.5-pro","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["file","image","text","audio","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1750118400,"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...","developer":"google","id":"google/gemini-2.5-flash","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Google: Gemini 2.5 Flash","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-06-17","root":"google/gemini-2.5-flash","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":200000,"created":1741305600,"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) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","developer":"perplexity","id":"perplexity/sonar-pro","is_provider_model":false,"last_updated":1784931903,"logo_url":null,"name":"Perplexity: Sonar Pro","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-03-07","root":"perplexity/sonar-pro","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}}],"object":"list"}