{"data":[{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"audio_pricing":null,"chinese_description":"DeepSeek V4.1 Flash 1017 是 DeepSeek V4.1 Flash 在 2026 年 10 月 17 日的快照版本，由 DeepSeek 通过 `deepseek-flash` API 模型名称提供服务。V4.1 Flash 是一款由 DeepSeek 开发的稀疏混合专家（Sparse Mixture-of-Experts）模型，也是首个基于该公司“因果编码器-解码器”（Causal Encoder-Decoder，简称 CED）架构构建的模型。该模型拥有 5520 亿（552B）参数规模，在处理输入时激活 80 亿（8B）参数，在处理输出时则激活 160 亿（16B）参数；这种非对称的参数激活方式，使得每个 Token 的计算开销相对于模型的总规模而言保持在较低水平。","context_length":1048576,"created":1792195200,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. ","developer":"deepseek","id":"deepseek/deepseek-v4.1-flash-1017","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"DeepSeek: DeepSeek V4.1 Flash 1017","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":"0.0000006","image":null,"input_cache_read":"0.000000003","input_cache_write":null,"prompt":"0.00000015","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-17","root":"deepseek/deepseek-v4.1-flash-1017","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","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":393216}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image","output_modalities":["text"],"tokenizer":"jev"},"audio_pricing":null,"chinese_description":"最新 TypeSafe System One。对共享 state 并行评估 typed questions，返回结构化 answers。实验性图像输入与 Box 定位。按输入 token 计费，输出免费。","context_length":64000,"created":1791936000,"description":"Newest TypeSafe System One release. Evaluates typed questions against a shared state and returns structured answers. Experimental image input and Box localization. Input tokens billed; output is free.","developer":"TypeSafe","id":"jev-1.14.0","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Jev 1.14.0","object":"model","owned_by":"TypeSafe","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000042","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-14","root":"jev-1.14.0","supported_parameters":[],"top_provider":{"context_length":64000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image","output_modalities":["text"],"tokenizer":"jev"},"audio_pricing":null,"chinese_description":"Jev 预览别名。目前指向 jev-1.14.0；有预览版时会领先于 jev-latest。","context_length":64000,"created":1791936000,"description":"Preview alias for Jev. Currently points at jev-1.14.0 and moves ahead of jev-latest when a preview exists.","developer":"TypeSafe","id":"jev-preview","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Jev Preview","object":"model","owned_by":"TypeSafe","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000042","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-14","root":"jev-preview","supported_parameters":[],"top_provider":{"context_length":64000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio","file","image","text","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"audio_pricing":null,"chinese_description":"Gemini 4 Argon 是 Google 的旗舰级推理模型，专为复杂的软件工程、深度的数学与科学问题求解以及自主多步智能体任务而打造。该模型经过训练，能够在长周期的多步任务中保持上下文连贯性，并将包含文本、表格、图表和图像的长篇文档整合为单一且基于事实依据的输出结果。它在金融、法律、编程及税务等领域的 Vals Index 评测中处于领先地位，并支持单次响应生成高达 100 万个 Token 的长文本输出。","context_length":1048576,"created":1791849600,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.","developer":"google","id":"google/gemini-4-argon","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Gemini 4 Argon","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":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-13","root":"google/gemini-4-argon","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","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":"Muse Wonder 是 Meta 推出的一款前沿推理模型，专为处理复杂的个人及专业智能体任务而设计。该模型支持文本、图像、视频、音频及 PDF 文档输入，并输出文本，同时具备 100 万 token 的上下文窗口。","context_length":1048576,"created":1791763200,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.","developer":"meta","id":"meta/muse-wonder","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Meta: Muse Wonder","object":"model","owned_by":"meta","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":"0.00002","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000004","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-12","root":"meta/muse-wonder","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","audio","video","file"],"instruct_type":null,"modality":"text+image+audio+video+file->text+image+audio+video","output_modalities":["text","image","audio","video"],"tokenizer":"Claude"},"audio_pricing":null,"chinese_description":"Knox Studio 模态路由（Modality Router，这是一个统一模型，涵盖了面向管理者/编辑的聊天功能，以及视频、图像、音乐、语音、音效、音频分离、变声、对齐、实时语音和视觉处理等多种模态。它能根据提示词（prompt）及附加媒体内容，将任务路由至相应的专业模型进行处理。","context_length":-1,"created":1791590400,"description":"Knox Studio modality router — one model for Manager/Editor chat plus video, image, music, speech, sound effects, isolation, voice conversion, alignment, realtime voice, and vision. Routes to specialist models from prompt and attached media.","developer":"KnoxChat","id":"knox/knox-studio","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792676997,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Knox-Studio","object":"model","owned_by":"KnoxChat","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":"0"},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-10","root":"knox/knox-studio","supported_parameters":["max_tokens","modality","response_format","session_id","temperature"],"top_provider":{"context_length":-1,"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":"Claude"},"audio_pricing":null,"chinese_description":"Claude Haiku 5.5 是 Anthropic 推出的一款轻量级、高速模型，专为处理大规模、成本敏感型任务（如摘要生成、子智能体操作及浏览器使用）而设计。作为 Claude Haiku 4.5 的升级版，该模型在编程、计算机操作及知识型任务处理方面表现更强，支持文本与图像输入，并具备 100 万 token 的上下文窗口。这是首款支持“投入力度”调节的 Haiku 模型。其“思考”功能采用自适应机制且默认开启，用户可通过调节投入力度，在深度、延迟与成本之间进行权衡；该功能亦可关闭，或设定为低、中、高三种投入力度。","context_length":1000000,"created":1791331200,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window. It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.","developer":"anthropic","id":"anthropic/claude-haiku-5.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Anthropic: Claude Haiku 5.5","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":"0.0000005","image":null,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-07","root":"anthropic/claude-haiku-5.5","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","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","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"x-ai"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1791244800,"description":"Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from [Grok Imagine Video 1.5](/x-ai/grok-imagine-video-1.5). It supports text-to-video and image-to-video, trading some quality for speed...","developer":"x-ai","id":"x-ai/grok-imagine-video-1.5-lite","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"SpaceXAI: Grok Imagine Video 1.5 Lite","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-06","root":"x-ai/grok-imagine-video-1.5-lite","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","audio"],"instruct_type":null,"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"audio_pricing":null,"chinese_description":"OpenAI 全双工语音模型，可同时收听与说话，支持自然打断，并将推理与工具调用委托给后端模型。语音按每分钟 $0.05 按秒计费，后端模型与工具用量另计。请使用 /v1/live/sessions WebSocket 或 WebRTC 端点。","context_length":128000,"created":1790812800,"description":"OpenAI full-duplex voice model for natural, interruptible conversations. It listens and speaks at the same time and delegates reasoning and tool use to a backend model. Billed $0.05 per minute of voice, per second; backend model and tool usage is billed separately. Use the /v1/live/sessions WebSocket or WebRTC endpoint.","developer":"OpenAI","id":"gpt-live-1","is_audio_model":false,"is_live_model":true,"is_provider_model":false,"is_video_model":false,"last_updated":1791254803,"live_pricing":{"per_minute":"0.05","per_second":"0.000833"},"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT Live 1","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","image":"0","input_cache_read":"0","input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-10-01","root":"gpt-live-1","supported_parameters":["function_calling","streaming"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"heygen"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1790726400,"description":"HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...","developer":"heygen","id":"heygen/heygen-video-1","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"HeyGen: HeyGen Video","object":"model","owned_by":"heygen","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-30","root":"heygen/heygen-video-1","supported_parameters":["prompt_enhancement"],"top_provider":{"context_length":0,"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"},"audio_pricing":null,"chinese_description":"GPT-6.1 Sol Pro 与 GPT-6.1 Sol 采用相同的底层模型，但将 `reasoning.mode` 设置为 `pro`，以便在处理复杂任务时提供更高质量的响应。关于成本的说明：Pro 模式在每次请求中消耗的推理 Token 数量远多于标准模式，因此，执行同一请求时，Pro 模式的成本通常是标准模式的数倍，且完成所需的时间也更长。该模式专为难度高、重要性强的任务而设计，在这些场景下，额外的准确性足以抵消其高昂的成本。对于日常编码、智能体（Agent）任务及对话交互等工作负载，建议使用 GPT-6.1 Sol。","context_length":1050000,"created":1790640000,"description":"GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.","developer":"openai","id":"openai/gpt-6.1-sol-pro","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-6.1 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":"0.00001","image":null,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-29","root":"openai/gpt-6.1-sol-pro","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"},"audio_pricing":null,"chinese_description":"GPT-6.1 Sol 是 OpenAI 对 GPT-6 Sol 的升级版本，在 GPT-6 系列中的定位低于旗舰级模型 GPT-6 Astra。适用于智能体编程、计算机操作、文档密集型专业工作以及多步骤业务流程自动化，能够以低得多的成本在这些任务中实现接近 Astra 级别的表现。与 GPT-6 Sol 相比，在执行智能体任务时的事实性错误更少，且在遵循明确限制条件和用户意图方面更为可靠。","context_length":1050000,"created":1790640000,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","developer":"openai","id":"openai/gpt-6.1-sol","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-6.1 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":"0.00001","image":null,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-29","root":"openai/gpt-6.1-sol","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"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"表现力最强的高质量语音合成，支持 90 余种语言，单次最多 10,000 字符。","context_length":0,"created":1790553600,"description":"Most emotive, high-quality speech synthesis across 90+ languages. Up to 10,000 characters per request.","developer":"ElevenLabs","id":"eleven_v4","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":10000,"max_duration_seconds":null,"name":"ElevenLabs v4","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-28","root":"eleven_v4","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.06"},"chinese_description":"表现力最强的实时语音合成，延迟约 100ms，支持 90 余种语言，单次最多 10,000 字符。","context_length":0,"created":1790553600,"description":"Most expressive real-time speech, about 100ms latency, across 90+ languages. Up to 10,000 characters per request.","developer":"ElevenLabs","id":"eleven_v4_turbo","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":10000,"max_duration_seconds":null,"name":"ElevenLabs v4 Turbo","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.06","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-28","root":"eleven_v4_turbo","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"audio_pricing":null,"chinese_description":"Claude Sonnet 5.5 是 Anthropic 旗下专为处理各类日常任务而设计的 Sonnet 级别模型，作为 Claude Sonnet 5 的直接升级版本，它在构建功能、修复错误以及撰写高质量文档、演示文稿和电子表格方面表现尤为出色，且在写作与沟通的清晰度上也优于前代产品。该模型始终处于“思考”模式，因此用户主要通过调节“投入程度”（effort）来平衡思考深度、响应延迟与运行成本；较低的投入设置能确保模型保持快速响应，从而满足日常智能体（agentic）交互流程的需求。","context_length":1000000,"created":1790553600,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor. Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.","developer":"anthropic","id":"anthropic/claude-sonnet-5.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Anthropic: Claude Sonnet 5.5","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":"0.00001","image":null,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-28","root":"anthropic/claude-sonnet-5.5","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"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"},"audio_pricing":null,"chinese_description":"GPT-6 Luna 是 OpenAI GPT-6 系列中一款快速且高性价比的模型，定位低于 GPT-6 Sol。它适用于聊天、分类及轻量级智能体（agentic）任务等高吞吐量且对延迟敏感的工作负载；而在投入更高推理算力的情况下，它也能胜任复杂的软件工程及计算机操作任务——这些任务以往通常需要 Sol 级别的模型来完成。该模型同样具备 GPT-6 系列在事实可靠性方面的提升，并延续了更清晰、更简洁的沟通风格。","context_length":1050000,"created":1790035200,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.","developer":"openai","id":"openai/gpt-6-luna","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-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":"0.0000005","image":null,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-22","root":"openai/gpt-6-luna","supported_parameters":["include_reasoning","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"},"audio_pricing":null,"chinese_description":"GPT-6 Luna Pro 与 GPT-6 Luna 采用相同的底层模型，但在服务时将 `reasoning.mode` 设置为 `pro`，从而在处理复杂任务时提供更高质量的响应。","context_length":1050000,"created":1790035200,"description":"GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.","developer":"openai","id":"openai/gpt-6-luna-pro","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-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":"0.0000005","image":null,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-22","root":"openai/gpt-6-luna-pro","supported_parameters":["include_reasoning","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"},"audio_pricing":null,"chinese_description":"GPT-6 Sol Pro 与 GPT-6 Sol 的底层模型相同，推理模式设置为 pro，以便对复杂任务做出更高质量的响应。","context_length":1050000,"created":1790035200,"description":"GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","developer":"openai","id":"openai/gpt-6-sol-pro","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-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":"0.00001","image":null,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-22","root":"openai/gpt-6-sol-pro","supported_parameters":["include_reasoning","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"},"audio_pricing":null,"chinese_description":"GPT-6 Sol 是 OpenAI GPT-6 系列中的高性价比高端模型，其定位介于旗舰级 GPT-6 Astra 与主打速度的 GPT-6 Luna 之间。该模型适用于高要求的专业工作、具备自主行动能力的编程任务、业务流程自动化以及计算机操作场景，尤其擅长处理基于实际代码库的长周期软件工程任务。它以低得多的成本实现了接近 Astra 级别的准确性与可靠性，并延续了 Astra 在技术及编程交流中清晰、简洁的沟通风格。","context_length":1050000,"created":1790035200,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.","developer":"openai","id":"openai/gpt-6-sol","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-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":"0.00001","image":null,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-22","root":"openai/gpt-6-sol","supported_parameters":["include_reasoning","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":"Claude"},"audio_pricing":null,"chinese_description":"Claude Opus 5.5 是 Anthropic 的旗舰模型，专为高难度的推理、编程及长周期智能体（agentic）任务而设计，是 Claude Opus 5 的升级版。该模型在处理大型代码库中的多步骤变更、代码审查与缺陷排查、金融与科学分析，以及解读信息密集的图表、示意图和截图方面表现尤为出色；与前代版本相比，它在引用数据和来源时更为严谨，仅在有据可查的情况下才会进行陈述。","context_length":1000000,"created":1790035200,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.","developer":"anthropic","id":"anthropic/claude-opus-5.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Anthropic: Claude Opus 5.5","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":"0.00002","image":null,"input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-22","root":"anthropic/claude-opus-5.5","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"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"},"audio_pricing":null,"chinese_description":"Grok 4.7 是 SpaceXAI 继 Grok 4.6 之后推出的旗舰模型，专用于编程、智能体（agentic）任务及知识型工作。该模型在处理长时间运行的软件工程任务、自我验证工作成果以及管理长上下文方面表现尤为出色，同时在起草文档和演示文稿等专业知识型工作上也较前代版本有所提升。","context_length":500000,"created":1789948800,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.","developer":"x-ai","id":"x-ai/grok-4.7","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"SpaceXAI: Grok 4.7","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":"0.0000048","image":null,"input_cache_read":"0.0000004","input_cache_write":null,"prompt":"0.0000016","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-21","root":"x-ai/grok-4.7","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image","output_modalities":["text"],"tokenizer":"jev"},"audio_pricing":null,"chinese_description":"TypeSafe System One。对共享 state 并行评估 typed questions，返回结构化 answers。实验性图像输入。按输入 token 计费，输出免费。","context_length":64000,"created":1789689600,"description":"TypeSafe System One. Evaluates typed questions against a shared state and returns structured answers. Experimental image input. Input tokens billed; output is free.","developer":"TypeSafe","id":"jev-1.13.0","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Jev 1.13.0","object":"model","owned_by":"TypeSafe","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000042","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-18","root":"jev-1.13.0","supported_parameters":[],"top_provider":{"context_length":64000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image","output_modalities":["text"],"tokenizer":"jev"},"audio_pricing":null,"chinese_description":"当前正式版 Jev 模型别名（jev-1.13.0）。","context_length":64000,"created":1789689600,"description":"Official alias for the current production Jev model (jev-1.13.0).","developer":"TypeSafe","id":"jev-latest","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Jev Latest","object":"model","owned_by":"TypeSafe","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000042","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-18","root":"jev-latest","supported_parameters":[],"top_provider":{"context_length":64000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"black-forest-labs"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1788998400,"description":"FLUX Video Edit [fast] takes a source video and an edit prompt and returns a precisely edited video. Add, remove, or replace objects and characters, rebuild the setting, edit on-screen...","developer":"black-forest-labs","id":"black-forest-labs/flux-video-edit","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Black Forest Labs: FLUX Video Edit","object":"model","owned_by":"black-forest-labs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-10","root":"black-forest-labs/flux-video-edit","supported_parameters":["safety_tolerance"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"audio_pricing":null,"chinese_description":"DeepSeek V4.1 Flash 由 DeepSeek 推出的稀疏混合专家（MoE）模型，属于 V4.1 系列中的高性价比版本。据 DeepSeek 称，该模型在性能、速度及任务完成耗时方面均优于 V4 Pro，因此其定位实际上高于而非低于此前的旗舰型号。","context_length":1048576,"created":1788998400,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task completion time, so it sits ahead of the previous flagship rather than beneath it.","developer":"deepseek","id":"deepseek/deepseek-v4.1-flash","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"DeepSeek: DeepSeek V4.1 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":"0.0000012","image":null,"input_cache_read":"0.000000006","input_cache_write":null,"prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-10","root":"deepseek/deepseek-v4.1-flash","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":384000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"audio_pricing":null,"chinese_description":"GPT Image 2.5 Flare 根据文本和图像输入生成图像，并针对快速、高质量的日常图像生成进行了优化。","context_length":131072,"created":1788912000,"description":"GPT Image 2.5 Flare generates images from text and image inputs, optimized for fast, high-quality everyday image generation.","developer":"knox","id":"gpt-image-2.5-flare","is_audio_model":false,"is_live_model":false,"is_provider_model":true,"is_video_model":false,"last_updated":1788918912,"live_pricing":null,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","max_characters":null,"max_duration_seconds":null,"name":"GPT Image 2.5 Flare","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,"pricing_original":null,"promotion":null,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-09-09","root":"gpt-image-2.5-flare","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":130924}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"audio_pricing":null,"chinese_description":"GPT Image 2.5 Sunburst 可根据文本和图像输入生成及编辑图像，并侧重于精确编辑。","context_length":131072,"created":1788912000,"description":"GPT Image 2.5 Sunburst generates and edits images from text and image inputs, with a focus on precise editing.","developer":"knox","id":"gpt-image-2.5-sunburst","is_audio_model":false,"is_live_model":false,"is_provider_model":true,"is_video_model":false,"last_updated":1788918911,"live_pricing":null,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","max_characters":null,"max_duration_seconds":null,"name":"GPT Image 2.5 Sunburst","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":"2.0","input_cache_write":"4.00","prompt":"8.00","web_search":""},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-09-09","root":"gpt-image-2.5-sunburst","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":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"audio_pricing":null,"chinese_description":"GPT-6 Astra 是 OpenAI 针对高要求端到端任务推出的旗舰模型。适用于高级分析、软件工程、深度研究、科学工作和文档创建，尤其擅长涉及计算机和浏览器使用的长周期智能体任务。","context_length":1050000,"created":1788480000,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","developer":"openai","id":"openai/gpt-6-astra","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-6 Astra","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":"0.00005","image":null,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-04","root":"openai/gpt-6-astra","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"},"audio_pricing":null,"chinese_description":"GPT-6 Astra Pro 与 GPT-6 Astra 使用相同的底层模型，但将 reasoning.mode 设置为 pro，以便在复杂任务上提供更高质量的响应。了解更多信息，请参阅 OpenAI 文档：https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_length":1050000,"created":1788480000,"description":"GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","developer":"openai","id":"openai/gpt-6-astra-pro","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT-6 Astra 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":"0.00005","image":null,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-04","root":"openai/gpt-6-astra-pro","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","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"minimax"},"audio_pricing":null,"chinese_description":"MiniMax H3 Max 是由 MiniMax 与 fal.ai 联合发布的视频生成模型。该模型基于 MiniMax H3 进一步训练而成，旨在实现更快速的文生视频（text-to-video）和图生视频（image-to-video）生成，并支持对首帧或尾帧关键帧进行控制。","context_length":4096,"created":1788307200,"description":"MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with controlled first-frame or last-frame keyframes.","developer":"minimax","id":"minimax/hailuo-3-max","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"MiniMax: H3 Max","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-02","root":"minimax/hailuo-3-max","supported_parameters":["aigc_watermark"],"top_provider":{"context_length":4096,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":"Muse Spark 1.3 Contributor 是 Meta 多模态推理模型的一个高性价比版本，专为实验、学习以及早期的智能体（agentic）、多智能体和编程工作流而设计。该模型能够跨长周期任务追踪信息、处理相互冲突的输入，并在必要时请求澄清或确认。相关的提示词（prompt）和输出内容可能会被用于改进 Meta 的产品。","context_length":1048576,"created":1788307200,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed. Prompts and outputs may be used to improve Meta’s products.","developer":"meta","id":"meta/muse-spark-1.3-contributor","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Meta: Muse Spark 1.3 Contributor","object":"model","owned_by":"meta","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":"0.0000002","image":null,"input_cache_read":"0.000000002","input_cache_write":null,"prompt":"0.0000001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-02","root":"meta/muse-spark-1.3-contributor","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":"Muse Spark 1.3 是 Meta 推出的一款多模态推理模型，专为长周期的智能体（agentic）、多智能体及编程工作流而设计。该模型旨在跨长时间跨度的任务中追踪信息、处理相互冲突的输入，并在必要时请求澄清或确认，同时强调执行过程的简洁高效。","context_length":1048576,"created":1788307200,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed, with an emphasis on concise execution.","developer":"meta","id":"meta/muse-spark-1.3","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Meta: Muse Spark 1.3","object":"model","owned_by":"meta","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":"0.00000425","image":null,"input_cache_read":"0.00000015","input_cache_write":null,"prompt":"0.00000125","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-02","root":"meta/muse-spark-1.3","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"audio_pricing":null,"chinese_description":"Gemini 3.8 Flash 是 Google 最智能的 Flash 模型，在软件工程、智能体任务和多步骤推理方面比 3.7 Flash 有了显著提升。","context_length":1048576,"created":1788307200,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","developer":"google","id":"google/gemini-3.8-flash","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Gemini 3.8 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":"0.00000375","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","prompt":"0.00000075","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-02","root":"google/gemini-3.8-flash","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","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"audio_pricing":null,"chinese_description":"Claude Fable 5.1 在各方面都超越了 Claude Fable 5，尤其在智能体编码、长时间运行的智能体工作流以及知识型工作方面提升显著：例如，长代码重构、前端和可视化代码生成，以及财务和分析任务。此外，它的计划和摘要也比 Fable 5 更加简洁。我们建议您在目前使用 Fable 5 的所有场景下直接升级到 Claude Fable 5.1，并在处理推理密集型任务时将其与 Opus 5 结合使用。","context_length":1000000,"created":1788220800,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","developer":"anthropic","id":"anthropic/claude-fable-5.1","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Anthropic: Claude Fable 5.1","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":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-09-01","root":"anthropic/claude-fable-5.1","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","audio","image"],"instruct_type":null,"modality":"text+audio+image->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"audio_pricing":null,"chinese_description":"OpenAI 蒸馏实时语音推理模型，速度更快、成本更低，支持工具调用，并改进了字母数字识别。请使用 /v1/realtime WebSocket 端点。","context_length":128000,"created":1787788800,"description":"OpenAI distilled speech-to-speech realtime reasoning model for faster, lower-cost voice interactions, with tool use and improved alphanumeric recognition. Use the /v1/realtime WebSocket endpoint.","developer":"OpenAI","id":"gpt-realtime-2.1-mini","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1787817895,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT Realtime 2.1 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":"2.4","image":"0.8","input_cache_read":"0.06","input_cache_write":null,"prompt":"0.6","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-27","root":"gpt-realtime-2.1-mini","supported_parameters":["function_calling","prompt_caching","reasoning","tools"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":"GLM-5.3-Flash 是 Z.ai 开发的原生多模态模型。它适用于高效编码和长时域智能体任务。其混合稀疏和线性注意力架构在保持精确的长时域行为的同时，降低了计算开销。","context_length":1048576,"created":1787702400,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","developer":"z-ai","id":"z-ai/glm-5.3-flash","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Z.ai: GLM 5.3 Flash","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":"0.00000025","image":null,"input_cache_read":"0.000000015","input_cache_write":null,"prompt":"0.000000075","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-26","root":"z-ai/glm-5.3-flash","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"alibaba"},"audio_pricing":null,"chinese_description":"Wan 3.0 是阿里巴巴推出的一款视频生成模型，支持文生视频、图生视频以及参考图引导的视频生成。该模型可生成分辨率为 480p、720p 或 1080p、时长在 2 到 30 秒之间的视频。","context_length":4096,"created":1787529600,"description":"Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.","developer":"alibaba","id":"alibaba/wan-3.0","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Alibaba: Wan 3.0","object":"model","owned_by":"alibaba","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-24","root":"alibaba/wan-3.0","supported_parameters":[],"top_provider":{"context_length":4096,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":"GLM-5.3 是 Z.ai 开发的大规模推理模型，专为复杂的软件工程和长周期智能体任务而设计。它支持文本输入输出，上下文窗口大小为 100 万个词元，并且在编码方面以及性能和词元效率的平衡方面都优于 GLM-5.2。","context_length":1048576,"created":1787011200,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","developer":"z-ai","id":"z-ai/glm-5.3","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Z.ai: GLM 5.3","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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-18","root":"z-ai/glm-5.3","supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"audio_pricing":null,"chinese_description":"Gemini 3.7 Flash是谷歌推出的一款多模态模型，专为快速代理工作流、编码及复杂多步骤推理设计。该模型适用于需要响应迅速且可靠多步骤问题解决的任务。","context_length":1048576,"created":1786579200,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","developer":"google","id":"google/gemini-3.7-flash","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Gemini 3.7 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":"0.000001875","image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","prompt":"0.000000375","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-13","root":"google/gemini-3.7-flash","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","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"bytedance"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1786492800,"description":"Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...","developer":"bytedance","id":"bytedance/seedance-2.0-mini","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ByteDance: Seedance 2.0 Mini","object":"model","owned_by":"bytedance","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-12","root":"bytedance/seedance-2.0-mini","supported_parameters":["watermark","req_key","return_last_frame"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"audio_pricing":null,"chinese_description":"DeepSeek V4 Pro 0813是DeepSeek推出的大型专家混合模型。这是DeepSeek V4 Pro的GA版。","context_length":1048576,"created":1786492800,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","developer":"deepseek","id":"deepseek/deepseek-v4-pro-0813","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"DeepSeek: DeepSeek V4 Pro 0813","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":"0.000000003625","input_cache_write":null,"prompt":"0.000000435","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-12","root":"deepseek/deepseek-v4-pro-0813","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","temperature","tool_choice","tools","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":"Qwen"},"audio_pricing":null,"chinese_description":"Qwen3.8 2.4T A95B是通义千问推出的开放权重稀疏专家混合模型，也是Qwen3.8 Max的开放权重版本，拥有2.4万亿总参数量中的950亿活跃参数，适用于编码、研究、复杂推理及代理工作流场景。","context_length":262144,"created":1786492800,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","developer":"qwen","id":"qwen/qwen3.8-2.4t-a95b","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Qwen: Qwen3.8 2.4T A95B","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":"0.000006","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-12","root":"qwen/qwen3.8-2.4t-a95b","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":52429}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"audio_pricing":null,"chinese_description":"Grok 4.6是SpaceX AI研发的最强大模型，在编程、知识工作及STEM领域表现卓越。","context_length":500000,"created":1786492800,"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","developer":"x-ai","id":"x-ai/grok-4.6","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"SpaceXAI: Grok 4.6","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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-12","root":"x-ai/grok-4.6","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","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":450000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"bytedance"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1786060800,"description":"Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...","developer":"bytedance","id":"bytedance/seedance-2.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ByteDance: Seedance 2.5","object":"model","owned_by":"bytedance","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-07","root":"bytedance/seedance-2.5","supported_parameters":["watermark","req_key","output_format"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"black-forest-labs"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1785801600,"description":"FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...","developer":"black-forest-labs","id":"black-forest-labs/flux-3-video","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Black Forest Labs: FLUX.3 Video","object":"model","owned_by":"black-forest-labs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-04","root":"black-forest-labs/flux-3-video","supported_parameters":["safety_tolerance","version"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"audio_pricing":null,"chinese_description":"Qwen3.8 Max 是阿里巴巴 Qwen3.8 系列的旗舰型号，是 Qwen3.8 Max Preview 的正式版继任者。它是一款多模态推理模型，旨在用于复杂推理、视觉理解、编码和智能体工作流程。","context_length":1000000,"created":1785715200,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding, coding, and agentic workflows.","developer":"qwen","id":"qwen/qwen3.8-max","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1788555965,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Qwen: Qwen3.8 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":"0.000006","image":null,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-08-03","root":"qwen/qwen3.8-max","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"audio_pricing":null,"chinese_description":null,"context_length":1048576,"created":1785456000,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.","developer":"deepseek","id":"deepseek/deepseek-v4-flash-0731","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"DeepSeek: DeepSeek V4 Flash 0731","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":"0.0000000028","input_cache_write":null,"prompt":"0.00000014","web_search":null},"pricing_in_display_units":false,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-31","root":"deepseek/deepseek-v4-flash-0731","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","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","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"runway"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1785283200,"description":"Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video workflows. It is designed for cinematic scene creation with strong motion quality, visual fidelity, and prompt adherence....","developer":"runway","id":"runway/gen-4.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Runway: Gen-4.5","object":"model","owned_by":"runway","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-29","root":"runway/gen-4.5","supported_parameters":["contentModeration"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"minimax"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1785283200,"description":"MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...","developer":"minimax","id":"minimax/hailuo-3","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"MiniMax: H3","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-29","root":"minimax/hailuo-3","supported_parameters":["aigc_watermark"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"runway"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1785283200,"description":"Runway Aleph 2.0 is an in-context video editing model from Runway. It applies text instructions and keyframe-guided edits across existing footage while preserving details that are not meant to change....","developer":"runway","id":"runway/aleph-2","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Runway: Aleph 2.0","object":"model","owned_by":"runway","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-29","root":"runway/aleph-2","supported_parameters":["contentModeration","keyframes"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"x-ai"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1784505600,"description":"Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject...","developer":"x-ai","id":"x-ai/grok-imagine-video-1.5","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"SpaceXAI: Grok Imagine Video 1.5","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-20","root":"x-ai/grok-imagine-video-1.5","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-16","root":"moonshotai/kimi-k3","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":943718}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-terra","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-09","root":"openai/gpt-5.6-terra-pro","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","audio","image"],"instruct_type":null,"modality":"text+audio+image->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"audio_pricing":null,"chinese_description":"OpenAI 实时语音模型，支持推理、工具调用，并改进了字母数字识别。请使用 /v1/realtime WebSocket 端点。","context_length":128000,"created":1782864000,"description":"OpenAI speech-to-speech realtime model with reasoning, tool use, and improved alphanumeric recognition. Use the /v1/realtime WebSocket endpoint.","developer":"OpenAI","id":"gpt-realtime-2.1","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1787763620,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"OpenAI: GPT Realtime 2.1","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":"24","image":"5","input_cache_read":"0.4","input_cache_write":null,"prompt":"4","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-07-01","root":"gpt-realtime-2.1","supported_parameters":["function_calling","prompt_caching","reasoning","tools"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"alibaba"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1782259200,"description":"HappyHorse 1.1 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...","developer":"alibaba","id":"alibaba/happyhorse-1.1","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Alibaba: HappyHorse 1.1","object":"model","owned_by":"alibaba","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-06-24","root":"alibaba/happyhorse-1.1","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-06-18","root":"google/gemini-3.1-flash-image","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-06-18","root":"google/gemini-3-pro-image","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-06-16","root":"z-ai/glm-5.2","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":""},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":true,"is_video_model":false,"last_updated":1788918911,"live_pricing":null,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","max_characters":null,"max_duration_seconds":null,"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,"pricing_original":null,"promotion":null,"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","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","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-05-31","root":"minimax/minimax-m3","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-05-28","root":"stepfun/step-3.7-flash","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"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-05-21","root":"qwen/qwen3.7-max","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"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"kwaivgi"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1777420800,"description":"Kling v3.0 Standard is a video generation model from Kuaishou. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for guided scene composition. Clips range from 3 to...","developer":"kwaivgi","id":"kwaivgi/kling-v3.0-std","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Kling: Video v3.0 Standard","object":"model","owned_by":"kwaivgi","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-29","root":"kwaivgi/kling-v3.0-std","supported_parameters":["negative_prompt","cfg_scale"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"kwaivgi"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1777420800,"description":"Kling v3.0 Pro is Kuaishou's premium video generation model, offering higher visual quality than the Standard tier. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for precise...","developer":"kwaivgi","id":"kwaivgi/kling-v3.0-pro","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Kling: Video v3.0 Pro","object":"model","owned_by":"kwaivgi","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-29","root":"kwaivgi/kling-v3.0-pro","supported_parameters":["negative_prompt","cfg_scale"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"google"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1776988800,"description":"Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1...","developer":"google","id":"google/veo-3.1-fast","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Veo 3.1 Fast","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-24","root":"google/veo-3.1-fast","supported_parameters":["personGeneration","aspectRatio","negativePrompt","conditioningScale","enhancePrompt"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"google"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1776902400,"description":"Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio...","developer":"google","id":"google/veo-3.1-lite","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Veo 3.1 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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-23","root":"google/veo-3.1-lite","supported_parameters":["personGeneration","aspectRatio","negativePrompt","conditioningScale","enhancePrompt"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"bytedance"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1776211200,"description":"Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...","developer":"bytedance","id":"bytedance/seedance-2.0-fast","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ByteDance: Seedance 2.0 Fast","object":"model","owned_by":"bytedance","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-15","root":"bytedance/seedance-2.0-fast","supported_parameters":["watermark","req_key"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"bytedance"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1776211200,"description":"Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...","developer":"bytedance","id":"bytedance/seedance-2.0","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ByteDance: Seedance 2.0","object":"model","owned_by":"bytedance","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-15","root":"bytedance/seedance-2.0","supported_parameters":["watermark","req_key"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["image","text","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-04-02","root":"google/gemma-4-31b-it","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":["text","image","video"],"instruct_type":null,"modality":"video","output_modalities":["video"],"tokenizer":"google"},"audio_pricing":null,"chinese_description":null,"context_length":0,"created":1774224000,"description":"Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...","developer":"google","id":"google/veo-3.1","is_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":true,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"Google: Veo 3.1","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-03-23","root":"google/veo-3.1","supported_parameters":["personGeneration","aspectRatio","negativePrompt","conditioningScale","enhancePrompt"],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-03-11","root":"nvidia/nemotron-3-super-120b-a12b","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1785846044,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-03-03","root":"openai/gpt-5.3-chat","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":["audio","file","image","text","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-02-19","root":"google/gemini-3.1-pro-preview","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":["audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"2.25"},"chinese_description":"直出音频对音频配音，保留表演并支持 90 余种语言，按片源分钟×语种计费，创建项目时预收第一种语言。","context_length":0,"created":1767225600,"description":"Direct audio-to-audio dubbing that preserves performance across 90+ languages. Billed per source minute per language; the first language is charged when the project is created.","developer":"ElevenLabs","id":"dubbing_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ElevenLabs Dubbing v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"2.25","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-01-01","root":"dubbing_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio"],"instruct_type":null,"modality":"audio","output_modalities":["text"],"tokenizer":"elevenlabs"},"audio_pricing":{"entity_detection":"0.12","keyterm_prompting":"0.10","per_hour":"0.44"},"chinese_description":"低延迟实时语音转文本（WebSocket），延迟约 150ms，按音频小时计费。","context_length":0,"created":1767225600,"description":"Low-latency realtime speech-to-text over WebSocket, about 150ms. Billed per audio hour.","developer":"ElevenLabs","id":"scribe_v2_realtime","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ElevenLabs Scribe v2 Realtime","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.44","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-01-01","root":"scribe_v2_realtime","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"面向语音代理的实时表现力模型，延迟约 280ms，单次最多 5,000 字符。","context_length":0,"created":1767225600,"description":"Realtime expressive speech for voice agents, about 280ms latency. Up to 5,000 characters per request.","developer":"ElevenLabs","id":"eleven_v3_conversational","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":5000,"max_duration_seconds":null,"name":"ElevenLabs v3 Conversational","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-01-01","root":"eleven_v3_conversational","supported_parameters":[],"top_provider":{"context_length":0,"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":"Claude"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2026-01-01","root":"knox/knox-ms","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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-12-09","root":"mistralai/devstral-2512","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":209715}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-12-01","root":"mistralai/mistral-large-2512","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":209715}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"chinese_description":null,"context_length":200000,"created":1761782400,"description":"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-10-30","root":"perplexity/sonar-pro-search","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":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-10-07","root":"google/gemini-2.5-flash-image","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","audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"finetune":"2.00","per_minute":"0.20"},"chinese_description":"最新一代 ElevenLabs 音乐模型，音质与可控性最佳，单次最长 5 分钟。","context_length":0,"created":1756684800,"description":"Latest ElevenLabs music model with the best quality and control. Up to 5 minutes per generation.","developer":"ElevenLabs","id":"music_v2_5","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":300,"name":"ElevenLabs Music v2.5","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.20","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-09-01","root":"music_v2_5","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-08-01","root":"mistralai/codestral-2508","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":204800}},{"architecture":{"input_modalities":["audio"],"instruct_type":null,"modality":"audio","output_modalities":["text"],"tokenizer":"elevenlabs"},"audio_pricing":{"entity_detection":"0.12","keyterm_prompting":"0.10","per_hour":"0.27"},"chinese_description":"语音转文本，支持 90 余种语言、词级时间戳与实体检测，按音频小时计费。","context_length":0,"created":1751328000,"description":"Speech-to-text transcription with 90+ languages, word-level timestamps, and optional entity detection. Billed per audio hour.","developer":"ElevenLabs","id":"scribe_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ElevenLabs Scribe v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.27","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-07-01","root":"scribe_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.15"},"chinese_description":"富有情感表现力的语音合成，支持 70 余种语言，单次最多 5,000 字符。","context_length":0,"created":1751328000,"description":"Emotionally rich, expressive speech across 70+ languages. Up to 5,000 characters per request.","developer":"ElevenLabs","id":"eleven_v3","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":5000,"max_duration_seconds":null,"name":"ElevenLabs v3","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.15","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-07-01","root":"eleven_v3","supported_parameters":[],"top_provider":{"context_length":0,"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"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-06-17","root":"google/gemini-2.5-pro","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","audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"finetune":"2.00","per_minute":"0.20"},"chinese_description":"更高保真度的音乐生成，结构与混音更稳定，单次最长 5 分钟。","context_length":0,"created":1746057600,"description":"Higher-fidelity music generation with stronger structure and mix. Up to 5 minutes per generation.","developer":"ElevenLabs","id":"music_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":300,"name":"ElevenLabs Music v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.20","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-05-01","root":"music_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"audio_pricing":null,"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_audio_model":false,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792531158,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":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,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2025-03-07","root":"perplexity/sonar-pro","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}},{"architecture":{"input_modalities":["audio","text"],"instruct_type":null,"modality":"audio","output_modalities":["text"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_hour":"0.27"},"chinese_description":"将语音与文本强制对齐，返回字符级和词级时间戳。单次最长 10 小时、最多 675,000 字符，按音频小时计费，费率与语音转文本相同。","context_length":0,"created":1730419200,"description":"Force-align spoken audio to a transcript for character- and word-level timestamps. Up to 10 hours and 675,000 characters per request. Billed per audio hour at the Speech to Text rate.","developer":"ElevenLabs","id":"forced_alignment","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":675000,"max_duration_seconds":36000,"name":"ElevenLabs Forced Alignment","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.27","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-11-01","root":"forced_alignment","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"超低延迟多语言语音，约 75ms，字符单价低于 v3 / Multilingual v2，单次最多 40,000 字符。","context_length":0,"created":1727740800,"description":"Ultra-low latency multilingual speech, about 75ms. Lower character price than v3 / Multilingual v2. Up to 40,000 characters per request.","developer":"ElevenLabs","id":"eleven_flash_v2_5","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":40000,"max_duration_seconds":null,"name":"ElevenLabs Flash v2.5","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-10-01","root":"eleven_flash_v2_5","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"finetune":"2.00","per_minute":"0.20"},"chinese_description":"根据提示词或作曲计划生成原创歌曲，单次最长 5 分钟。","context_length":0,"created":1725148800,"description":"Compose original songs from a prompt or composition plan. Up to 5 minutes per generation.","developer":"ElevenLabs","id":"music_v1","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":300,"name":"ElevenLabs Music v1","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.20","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-09-01","root":"music_v1","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"已弃用的低延迟多语言模型，建议改用 Flash v2.5，单次最多 40,000 字符。","context_length":0,"created":1725148800,"description":"Deprecated low-latency multilingual model. Prefer Flash v2.5. Up to 40,000 characters per request.","developer":"ElevenLabs","id":"eleven_turbo_v2_5","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1791670879,"live_pricing":null,"logo_url":null,"max_characters":10000,"max_duration_seconds":null,"name":"ElevenLabs Turbo v2.5","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-09-01","root":"eleven_turbo_v2_5","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"超低延迟英语语音，约 75ms，字符单价低于 v3 / Multilingual v2，单次最多 30,000 字符。","context_length":0,"created":1720051200,"description":"Ultra-low latency English speech, about 75ms. Lower character price than v3 / Multilingual v2. Up to 30,000 characters per request.","developer":"ElevenLabs","id":"eleven_flash_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":30000,"max_duration_seconds":null,"name":"ElevenLabs Flash v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-07-04","root":"eleven_flash_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.10"},"chinese_description":"已弃用的低延迟英语模型，建议改用 Flash v2，单次最多 30,000 字符。","context_length":0,"created":1709251200,"description":"Deprecated low-latency English model. Prefer Flash v2. Up to 30,000 characters per request.","developer":"ElevenLabs","id":"eleven_turbo_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1791670879,"live_pricing":null,"logo_url":null,"max_characters":10000,"max_duration_seconds":null,"name":"ElevenLabs Turbo v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.10","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-03-01","root":"eleven_turbo_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"0.17"},"chinese_description":"根据文本提示生成免版税音效，单次 0.5–30 秒，按生成音频分钟计费。","context_length":0,"created":1705881600,"description":"Royalty-free sound effects from a text prompt. 0.5–30 seconds per generation. Billed per generated audio minute.","developer":"ElevenLabs","id":"eleven_text_to_sound_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":30,"name":"ElevenLabs Sound Effects v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.17","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2024-01-22","root":"eleven_text_to_sound_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"0.17"},"chinese_description":"多语言变声模型，转换音色并保留情绪、节奏与表达，单次最长 10 分钟，按音频分钟计费。","context_length":0,"created":1699920000,"description":"Multilingual voice changer. Transform audio from one voice to another while keeping emotion, timing, and delivery. Up to 10 minutes per request. Billed per audio minute.","developer":"ElevenLabs","id":"eleven_multilingual_sts_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":600,"name":"ElevenLabs Multilingual STS v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.17","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2023-11-14","root":"eleven_multilingual_sts_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"0.17"},"chinese_description":"从音频或视频中去除背景噪声并分离人声，单次最长 1 小时，按音频分钟计费。","context_length":0,"created":1699920000,"description":"Remove background noise and isolate speech from audio or video. Up to 1 hour per request. Billed per audio minute.","developer":"ElevenLabs","id":"audio_isolation","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":3600,"name":"ElevenLabs Voice Isolator","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.17","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2023-11-14","root":"audio_isolation","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio","video"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"0.38"},"chinese_description":"级联 TTS 配音，支持 70 余种语言，按片源分钟×语种计费，创建项目时预收第一种语言。","context_length":0,"created":1699920000,"description":"Cascaded TTS dubbing into 70+ languages. Billed per source minute per language; the first language is charged when the project is created.","developer":"ElevenLabs","id":"dubbing_v1","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":null,"name":"ElevenLabs Dubbing v1","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.38","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2023-11-14","root":"dubbing_v1","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["audio"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_minute":"0.17"},"chinese_description":"英语变声模型，转换音色并保留情绪、节奏与表达，单次最长 10 分钟，按音频分钟计费。","context_length":0,"created":1690848000,"description":"English-only voice changer. Transform audio from one voice to another while keeping emotion, timing, and delivery. Up to 10 minutes per request. Billed per audio minute.","developer":"ElevenLabs","id":"eleven_english_sts_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":null,"max_duration_seconds":600,"name":"ElevenLabs English STS v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.17","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2023-08-01","root":"eleven_english_sts_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"audio","output_modalities":["audio"],"tokenizer":"elevenlabs"},"audio_pricing":{"per_thousand_characters":"0.15"},"chinese_description":"29 种语言的稳定拟真朗读，默认 TTS 模型，单次最多 10,000 字符。","context_length":0,"created":1690848000,"description":"Stable, lifelike narration in 29 languages. Default TTS model. Up to 10,000 characters per request.","developer":"ElevenLabs","id":"eleven_multilingual_v2","is_audio_model":true,"is_live_model":false,"is_provider_model":false,"is_video_model":false,"last_updated":1792691672,"live_pricing":null,"logo_url":null,"max_characters":10000,"max_duration_seconds":null,"name":"ElevenLabs Multilingual v2","object":"model","owned_by":"ElevenLabs","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","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.15","web_search":null},"pricing_in_display_units":true,"pricing_original":null,"promotion":null,"provider_info":null,"release_date":"2023-08-01","root":"eleven_multilingual_v2","supported_parameters":[],"top_provider":{"context_length":0,"is_moderated":false,"max_completion_tokens":null}}],"object":"list"}