> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-HK/llms.txt # ![Qiniu 標誌](https://models.dev/logos/qiniu-ai.svg)Qiniu 透過 Mastra 的模型路由器存取 91 個 Qiniu 模型。系統會自動使用 `QINIU_API_KEY` 環境變數進行驗證。 詳情請參閱[Qiniu 文件](https://developer.qiniu.com/aitokenapi)。 ```bash QINIU_API_KEY=your-api-key ``` ```typescript import { Agent } from '@mastra/core/agent' const agent = new Agent({ id: 'my-agent', name: 'My Agent', instructions: 'You are a helpful assistant', model: 'qiniu-ai/MiniMax-M1', }) // Generate a response const response = await agent.generate('Hello!') // Stream a response const stream = await agent.stream('Tell me a story') for await (const chunk of stream) { console.log(chunk) } ``` > **資訊:** Mastra 使用與 OpenAI 相容的 `/chat/completions` 端點。部分 Provider 專屬功能可能無法使用，詳情請參閱[Qiniu 文件](https://developer.qiniu.com/aitokenapi)。 ## 模型 | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | --------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `qiniu-ai/claude-3.5-haiku` | 200K | | | | | | — | — | | `qiniu-ai/claude-3.5-sonnet` | 200K | | | | | | — | — | | `qiniu-ai/claude-3.7-sonnet` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.0-opus` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.0-sonnet` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.1-opus` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.5-haiku` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.5-opus` | 200K | | | | | | — | — | | `qiniu-ai/claude-4.5-sonnet` | 200K | | | | | | — | — | | `qiniu-ai/deepseek-r1` | 128K | | | | | | — | — | | `qiniu-ai/deepseek-r1-0528` | 128K | | | | | | — | — | | `qiniu-ai/deepseek-v3` | 128K | | | | | | — | — | | `qiniu-ai/deepseek-v3-0324` | 128K | | | | | | — | — | | `qiniu-ai/deepseek-v3.1` | 128K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-math-v2` | 160K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-v3.1-terminus` | 128K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-v3.1-terminus-thinking` | 128K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-v3.2-251201` | 128K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-v3.2-exp` | 128K | | | | | | — | — | | `qiniu-ai/deepseek/deepseek-v3.2-exp-thinking` | 128K | | | | | | — | — | | `qiniu-ai/doubao-1.5-pro-32k` | 128K | | | | | | — | — | | `qiniu-ai/doubao-1.5-thinking-pro` | 128K | | | | | | — | — | | `qiniu-ai/doubao-1.5-vision-pro` | 128K | | | | | | — | — | | `qiniu-ai/doubao-seed-1.6` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-1.6-flash` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-1.6-thinking` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-2.0-code` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-2.0-lite` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-2.0-mini` | 256K | | | | | | — | — | | `qiniu-ai/doubao-seed-2.0-pro` | 256K | | | | | | — | — | | `qiniu-ai/gemini-2.0-flash` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-2.0-flash-lite` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-2.5-flash` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-2.5-flash-image` | 33K | | | | | | — | — | | `qiniu-ai/gemini-2.5-flash-lite` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-2.5-pro` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-3.0-flash-preview` | 1.0M | | | | | | — | — | | `qiniu-ai/gemini-3.0-pro-image-preview` | 33K | | | | | | — | — | | `qiniu-ai/gemini-3.0-pro-preview` | 1.0M | | | | | | — | — | | `qiniu-ai/glm-4.5` | 131K | | | | | | — | — | | `qiniu-ai/glm-4.5-air` | 131K | | | | | | — | — | | `qiniu-ai/gpt-oss-120b` | 128K | | | | | | — | — | | `qiniu-ai/gpt-oss-20b` | 128K | | | | | | — | — | | `qiniu-ai/kimi-k2` | 128K | | | | | | — | — | | `qiniu-ai/kling-v2-6` | 100.0M | | | | | | — | — | | `qiniu-ai/meituan/longcat-flash-chat` | 131K | | | | | | — | — | | `qiniu-ai/meituan/longcat-flash-lite` | 256K | | | | | | — | — | | `qiniu-ai/mimo-v2-flash` | 256K | | | | | | $0.10 | $0.30 | | `qiniu-ai/MiniMax-M1` | 1.0M | | | | | | — | — | | `qiniu-ai/minimax/minimax-m2` | 200K | | | | | | — | — | | `qiniu-ai/minimax/minimax-m2.1` | 205K | | | | | | — | — | | `qiniu-ai/minimax/minimax-m2.5` | 205K | | | | | | — | — | | `qiniu-ai/minimax/minimax-m2.5-highspeed` | 205K | | | | | | — | — | | `qiniu-ai/moonshotai/kimi-k2-0905` | 256K | | | | | | — | — | | `qiniu-ai/moonshotai/kimi-k2-thinking` | 256K | | | | | | — | — | | `qiniu-ai/moonshotai/kimi-k2.5` | 256K | | | | | | — | — | | `qiniu-ai/openai/gpt-5` | 400K | | | | | | — | — | | `qiniu-ai/openai/gpt-5.2` | 400K | | | | | | — | — | | `qiniu-ai/qwen-max-2025-01-25` | 128K | | | | | | — | — | | `qiniu-ai/qwen-turbo` | 1.0M | | | | | | — | — | | `qiniu-ai/qwen-vl-max-2025-01-25` | 128K | | | | | | — | — | | `qiniu-ai/qwen2.5-vl-72b-instruct` | 128K | | | | | | — | — | | `qiniu-ai/qwen2.5-vl-7b-instruct` | 128K | | | | | | — | — | | `qiniu-ai/qwen3-235b-a22b` | 128K | | | | | | — | — | | `qiniu-ai/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | — | — | | `qiniu-ai/qwen3-235b-a22b-thinking-2507` | 262K | | | | | | — | — | | `qiniu-ai/qwen3-30b-a3b` | 40K | | | | | | — | — | | `qiniu-ai/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | — | — | | `qiniu-ai/qwen3-30b-a3b-thinking-2507` | 126K | | | | | | — | — | | `qiniu-ai/qwen3-32b` | 40K | | | | | | — | — | | `qiniu-ai/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | — | — | | `qiniu-ai/qwen3-max` | 262K | | | | | | — | — | | `qiniu-ai/qwen3-max-preview` | 256K | | | | | | — | — | | `qiniu-ai/qwen3-next-80b-a3b-instruct` | 131K | | | | | | — | — | | `qiniu-ai/qwen3-next-80b-a3b-thinking` | 131K | | | | | | — | — | | `qiniu-ai/qwen3-vl-30b-a3b-thinking` | 128K | | | | | | — | — | | `qiniu-ai/qwen3.5-397b-a17b` | 256K | | | | | | — | — | | `qiniu-ai/stepfun-ai/gelab-zero-4b-preview` | 8K | | | | | | — | — | | `qiniu-ai/stepfun/step-3.5-flash` | 64K | | | | | | — | — | | `qiniu-ai/x-ai/grok-4-fast` | 2.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-4-fast-non-reasoning` | 2.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-4-fast-reasoning` | 2.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-4.1-fast` | 2.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-4.1-fast-non-reasoning` | 2.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-4.1-fast-reasoning` | 20.0M | | | | | | — | — | | `qiniu-ai/x-ai/grok-code-fast-1` | 256K | | | | | | — | — | | `qiniu-ai/xiaomi/mimo-v2-flash` | 256K | | | | | | $0.10 | $0.30 | | `qiniu-ai/z-ai/autoglm-phone-9b` | 13K | | | | | | — | — | | `qiniu-ai/z-ai/glm-4.6` | 200K | | | | | | — | — | | `qiniu-ai/z-ai/glm-4.7` | 200K | | | | | | — | — | | `qiniu-ai/z-ai/glm-5` | 200K | | | | | | — | — | ## 進階設定 ### 自訂標頭 ```typescript const agent = new Agent({ id: 'custom-agent', name: 'custom-agent', model: { url: 'https://api.qnaigc.com/v1', id: 'qiniu-ai/MiniMax-M1', apiKey: process.env.QINIU_API_KEY, headers: { 'X-Custom-Header': 'value', }, }, }) ``` ### 動態選擇模型 ```typescript const agent = new Agent({ id: 'dynamic-agent', name: 'Dynamic Agent', model: ({ requestContext }) => { const useAdvanced = requestContext.task === 'complex' return useAdvanced ? 'qiniu-ai/z-ai/glm-5' : 'qiniu-ai/MiniMax-M1' }, }) ```