> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-TW/llms.txt # ![InferX 標誌](https://models.dev/logos/inferx.svg)InferX 透過 Mastra 的模型路由器存取 6 個 InferX 模型。系統會自動使用 `INFERX_API_KEY` 環境變數完成身分驗證。 如需進一步了解,請參閱[InferX 文件](https://model.inferx.net/endpoints)。 ```bash INFERX_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: 'inferx/google/gemma-4-31b-it-fp8', }) // 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` endpoint。部分 Provider 特有功能可能無法使用,詳情請參閱[InferX 文件](https://model.inferx.net/endpoints)。 ## 模型 | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `inferx/google/gemma-4-31b-it-fp8` | 262K | | | | | | — | — | | `inferx/qwen/qwen3.5-122b-a10b-nvfp4` | 256K | | | | | | — | — | | `inferx/qwen/qwen3.6-27b-fp8` | 262K | | | | | | — | — | | `inferx/qwen/qwen3.6-35b-a3b-fp8` | 262K | | | | | | — | — | | `inferx/qwen3-coder-next-fp8` | 256K | | | | | | — | — | | `inferx/qwen3-coder-next-fp8-1m` | 1.0M | | | | | | — | — | ## 進階設定 ### 自訂標頭 ```typescript const agent = new Agent({ id: 'custom-agent', name: 'custom-agent', model: { url: 'https://model.inferx.net/endpoints/v1', id: 'inferx/google/gemma-4-31b-it-fp8', apiKey: process.env.INFERX_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 ? 'inferx/qwen3-coder-next-fp8-1m' : 'inferx/google/gemma-4-31b-it-fp8' }, }) ```