# ![Sarvam AI logo](https://models.dev/logos/sarvam.svg)Sarvam AI

Access 2 Sarvam AI models through Mastra's model router. Authentication is handled automatically using the `SARVAM_API_KEY` environment variable.

Learn more in the [Sarvam AI documentation](https://docs.sarvam.ai).

```bash
SARVAM_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: "sarvam/sarvam-105b"
});

// 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 [Sarvam AI documentation](https://docs.sarvam.ai) for details.

## Models

| Model                | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| -------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `sarvam/sarvam-105b` | 131K    |       |           |       |       |       | —          | —           |
| `sarvam/sarvam-30b`  | 66K     |       |           |       |       |       | —          | —           |

## Advanced configuration

### Custom headers

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.sarvam.ai/v1",
    id: "sarvam/sarvam-105b",
    apiKey: process.env.SARVAM_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
      ? "sarvam/sarvam-30b"
      : "sarvam/sarvam-105b";
  }
});
```