# ![StepFun logo](https://models.dev/logos/stepfun-ai.svg)StepFun Access 2 StepFun models through Mastra's model router. Authentication is handled automatically using the `STEPFUN_API_KEY` environment variable. Learn more in the [StepFun documentation](https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code). ```bash STEPFUN_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: "stepfun-ai/step-3.5-flash" }); // 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 [StepFun documentation](https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code) for details. ## Models | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | -------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `stepfun-ai/step-3.5-flash` | 256K | | | | | | $0.10 | $0.29 | | `stepfun-ai/step-3.5-flash-2603` | 256K | | | | | | $0.10 | $0.30 | ## Advanced configuration ### Custom headers ```typescript const agent = new Agent({ id: "custom-agent", name: "custom-agent", model: { url: "https://api.stepfun.ai/step_plan/v1", id: "stepfun-ai/step-3.5-flash", apiKey: process.env.STEPFUN_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 ? "stepfun-ai/step-3.5-flash-2603" : "stepfun-ai/step-3.5-flash"; } }); ```