> Discover all available pages from the documentation index: https://mastra.zisheng.pro/en/llms.txt # ![Hetzner logo](https://models.dev/logos/hetzner.svg)Hetzner Access 1 Hetzner model through Mastra's model router. Authentication is handled automatically using the `HETZNER_API_KEY` environment variable. Learn more in the [Hetzner documentation](https://experiments.hetzner.com). ```bash HETZNER_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: "hetzner/Qwen/Qwen3.6-35B-A3B-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); } ``` > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Hetzner documentation](https://experiments.hetzner.com) for details. ## Models | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `hetzner/Qwen/Qwen3.6-35B-A3B-FP8` | 262K | | | | | | — | — | ## Advanced configuration ### Custom headers ```typescript const agent = new Agent({ id: "custom-agent", name: "custom-agent", model: { url: "https://inference.hetzner.com/api/v1", id: "hetzner/Qwen/Qwen3.6-35B-A3B-FP8", apiKey: process.env.HETZNER_API_KEY, headers: { "X-Custom-Header": "value" } } }); ``` ### Dynamic model selection ```typescript const agent = new Agent({ id: "dynamic-agent", name: "Dynamic Agent", model: ({ requestContext }) => { const useAdvanced = requestContext.task === "complex"; return useAdvanced ? "hetzner/Qwen/Qwen3.6-35B-A3B-FP8" : "hetzner/Qwen/Qwen3.6-35B-A3B-FP8"; } }); ```