# 01router — 网关 API 文档

> 一个 REST API 统一调用 fal.ai、Replicate、WaveSpeedAI、KIE AI、APIMart、EvoLink、AtlasCloud、Vercel AI Gateway、OpenRouter 上的图片、视频、音频与对话模型。

Base URL: https://01router.com/api/v1
Documentation: https://01router.com/zh/docs
Index: https://01router.com/docs/llms.txt?locale=zh
Full reference: https://01router.com/docs/llms-full.txt?locale=zh

生成、任务记录、取消与对话需要密钥；模型目录、提示词和报价公开可读。请将 API Key 保存在服务端。

响应仅用于说明结构；ID、用量、价格和结果以实际请求为准。

- [快速开始](https://01router.com/docs/llms-full.txt?locale=zh&section=quickstart): 选择模型、发送请求、获取结果。从这里完成第一次 API 调用。
- [鉴权](https://01router.com/docs/llms-full.txt?locale=zh&section=auth): 以 Bearer Token 方式发送 API Key，费用从 Key 所属账户的积分中扣除。
- [项目机制](https://01router.com/docs/llms-full.txt?locale=zh&section=projects): 项目是接入的基本单位：每个项目有自己的 API Key、模型范围、供应商和价格比例。用项目的 Key 调用接口时，项目配置会自动生效；你的前端还能用项目 ID 拉取带售价的模型目录。
- [创建生成任务](https://01router.com/docs/llms-full.txt?locale=zh&section=create): POST /api/v1/generations. 传入模型 ID、统一输入参数，可选指定供应商 slug。接口立即返回任务 ID；同步类供应商的图片模型可能直接返回成功结果。
- [获取结果](https://01router.com/docs/llms-full.txt?locale=zh&section=poll): GET /api/v1/generations/{id}. 每隔几秒轮询，直到 status 为 succeeded 或 failed。输出链接由供应商托管，可能过期，请及时下载保存；也可以传 callback_url 接收推送。
- [任务列表](https://01router.com/docs/llms-full.txt?locale=zh&section=list): GET /api/v1/generations. 分页查询你的生成记录（page、pageSize）
- [取消任务](https://01router.com/docs/llms-full.txt?locale=zh&section=cancel): POST /api/v1/generations/{id}/cancel. POST /generations/:id/cancel 会请求供应商停止进行中的任务。供应商确认后，任务以 failed 结束（error 为 "Canceled by user"），积分全额退还。目前支持 fal（仅排队中的任务）和 Replicate；其他供应商或已结束的任务返回 409 not_cancelable。
- [OpenAI 兼容生图](https://01router.com/docs/llms-full.txt?locale=zh&section=images): POST /api/v1/images/generations. POST /images/generations 兼容 OpenAI 图片接口，OpenAI SDK、LobeChat、Cherry Studio、Dify、n8n 都能直接调用这里的图片模型。size 会映射为最接近的 aspect_ratio，n 映射为 num_images，模型的其他参数可作为额外字段传入。最多等待约 110 秒，超时返回 504 和任务 id，可继续轮询。
- [对话补全](https://01router.com/docs/llms-full.txt?locale=zh&section=chat): POST /api/v1/chat/completions. 对话模型（GPT、Claude、Gemini、Grok、DeepSeek 等）使用 OpenAI Chat Completions 格式，官方 OpenAI SDK 将 base URL 设为 https://01router.com/api/v1 即可调用。传 "stream": true 获得 SSE 流式输出。调用前按输入 + max_tokens（未传时为 4096）预扣积分，回复结束后按实际 token 用量结算；请求 ID 会出现在 X-Gateway-Request-Id 响应头和任务日志中。
- [报价](https://01router.com/docs/llms-full.txt?locale=zh&section=quote): POST /api/v1/quote. 请求体与创建任务相同。返回按价格排序的可用供应商，以及无法处理该请求的供应商及原因。
- [模型列表](https://01router.com/docs/llms-full.txt?locale=zh&section=models): GET /api/v1/models. 通过 GET /api/v1/models 获取平台模型、参数与价格；传入 project 查询参数获取指定项目模型，可用 type=video|image|audio|chat 筛选。
- [查询单个模型](https://01router.com/docs/llms-full.txt?locale=zh&section=model-detail): GET /api/v1/models/{slug}. 模型对象包含 slug、name、type、vendor、params 和 providers。供应商条目包含其实际参数和价格档位。
- [项目模型目录](https://01router.com/docs/llms-full.txt?locale=zh&section=project-models): GET /api/v1/models. 使用 GET /api/v1/models?project={id} 读取指定项目的公开模型目录，包含选定供应商与转售价格。不传 project 时返回平台模型；可追加 &type=video 等类型筛选参数。
- [提示词 API](https://01router.com/docs/llms-full.txt?locale=zh&section=prompts): GET /api/v1/prompts. 公开只读接口，无需 API Key，不扣除积分。复用提示词库中已启用模型的已发布示例，支持按模型、来源和场景组合筛选。
- [提示词详情](https://01router.com/docs/llms-full.txt?locale=zh&section=prompt-detail): GET /api/v1/prompts/{id}. 将列表中的 id 替换 <prompt_id>。详情直接返回提示词对象，包含 object: "prompt" 及 data 单条记录中的同名字段，不再包裹 data。只返回当前语言下可公开访问的记录。
- [任务回调](https://01router.com/docs/llms-full.txt?locale=zh&section=callback): 传入 callback_url（公网 https 地址），任务成功或失败后我们会把最终的 generation 对象 POST 过去，失败按退避重试最多 5 次，无需轮询。
- [供应商路由](https://01router.com/docs/llms-full.txt?locale=zh&section=routing): 未指定 provider 时，我们会用每个供应商支持的取值校验参数并报价，提交给最便宜的供应商；提交失败会退款并尝试下一个（最多 3 家）。指定 provider 时只会发往该供应商。
- [计费](https://01router.com/docs/llms-full.txt?locale=zh&section=billing): 任务提交时按所选供应商对应参数的价格扣除积分（视频按秒、图片按张或按次）。失败或超时的任务会自动退还积分。
- [音频模型](https://01router.com/docs/llms-full.txt?locale=zh&section=audio): 音乐（Suno）和语音合成（Gemini TTS）模型与图片、视频一样走 /generations：先创建任务再轮询，输出为音频文件 URL。
- [错误码](https://01router.com/docs/llms-full.txt?locale=zh&section=errors): 请同时检查 HTTP 状态和 error.message。部分限流响应使用 message 包装并附带 Retry-After。相同 HTTP 状态的错误码可能随接口不同。

## 模型文档

- [Grok Imagine Video 1.5](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=grok-imagine-video-1.5): video; model=grok-imagine-video-1.5; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Seedance 2.5](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=seedance-2.5): video; model=seedance-2.5; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Grok Imagine Video 1.5 Lite](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=grok-imagine-video-1.5-lite): video; model=grok-imagine-video-1.5-lite; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [MiniMax H3 Max](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=minimax-h3-max): video; model=minimax-h3-max; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Seedance 2.0](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=seedance-2.0): video; model=seedance-2.0; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Seedance 2.0 Mini](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=seedance-2.0-mini): video; model=seedance-2.0-mini; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [MiniMax H3](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=minimax-h3): video; model=minimax-h3; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Wan 3.0](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=wan-3.0): video; model=wan-3.0; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Kling 3.0 Turbo](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=kling-3.0-turbo): video; model=kling-3.0-turbo; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Gemini Omni Flash 1.1](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gemini-omni-flash-1.1): video; model=gemini-omni-flash-1.1; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [HappyHorse 1.1](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=happyhorse-1.1): video; model=happyhorse-1.1; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [FLUX 3 Video](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=flux-3-video): video; model=flux-3-video; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [LTX-2.5 Fast](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=ltx-2.5-fast): video; model=ltx-2.5-fast; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Wan 2.7](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=wan-2.7): video; model=wan-2.7; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Veo 3.1](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=veo-3.1): video; model=veo-3.1; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [GPT Image 2.5 Flare](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-image-2.5-flare): image; model=gpt-image-2.5-flare; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [GPT Image 2.5 Sunburst](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-image-2.5-sunburst): image; model=gpt-image-2.5-sunburst; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Nano Banana 2.1](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=nano-banana-2.1): image; model=nano-banana-2.1; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Seedream 5.0 Pro](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=seedream-5.0-pro): image; model=seedream-5.0-pro; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Nano Banana 2](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=nano-banana-2): image; model=nano-banana-2; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Seedream 5.0 Flash](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=seedream-5.0-flash): image; model=seedream-5.0-flash; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Qwen Image 3.0](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=qwen-image-3.0): image; model=qwen-image-3.0; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Grok Imagine Image 2.0](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=grok-imagine-image-2.0): image; model=grok-imagine-image-2.0; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Nano Banana Pro](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=nano-banana-pro): image; model=nano-banana-pro; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [FLUX.2 Pro](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=flux-2-pro): image; model=flux-2-pro; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Ideogram 4.5](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=ideogram-4.5): image; model=ideogram-4.5; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Recraft V4](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=recraft-v4): image; model=recraft-v4; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Z-Image Turbo](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=z-image-turbo): image; model=z-image-turbo; POST /api/v1/generations, POST /api/v1/images/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [GPT-6 Astra](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-6-astra): chat; model=gpt-6-astra; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [GPT-6 Sol](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-6-sol): chat; model=gpt-6-sol; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [GPT-6 Luna](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-6-luna): chat; model=gpt-6-luna; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [GPT-5.6 Sol](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-5.6-sol): chat; model=gpt-5.6-sol; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [GPT-5.6 Terra](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-5.6-terra): chat; model=gpt-5.6-terra; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [GPT-5.6 Luna](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gpt-5.6-luna): chat; model=gpt-5.6-luna; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Claude Opus 5.5](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=claude-opus-5.5): chat; model=claude-opus-5.5; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Claude Sonnet 5.5](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=claude-sonnet-5.5): chat; model=claude-sonnet-5.5; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Gemini 4 Argon](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gemini-4-argon): chat; model=gemini-4-argon; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Gemini 3.8 Flash](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gemini-3.8-flash): chat; model=gemini-3.8-flash; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Grok 4.7](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=grok-4.7): chat; model=grok-4.7; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [DeepSeek V4.1 Flash](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=deepseek-v4.1-flash): chat; model=deepseek-v4.1-flash; POST /api/v1/chat/completions, GET /api/v1/models/{slug}
- [Suno V6](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=suno-v6): audio; model=suno-v6; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [Gemini 3.8 Flash TTS](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=gemini-3.8-flash-tts): audio; model=gemini-3.8-flash-tts; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [ElevenLabs Eleven v4](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=elevenlabs-tts-v4): audio; model=elevenlabs-tts-v4; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}
- [ElevenLabs Eleven v4 Turbo](https://01router.com/docs/llms-full.txt?locale=zh&section=model&model=elevenlabs-tts-v4-turbo): audio; model=elevenlabs-tts-v4-turbo; POST /api/v1/generations, GET /api/v1/generations/{id}, POST /api/v1/generations/{id}/cancel, POST /api/v1/quote, GET /api/v1/models/{slug}