# ![Groq logo](https://models.dev/logos/groq.svg)Groq

Access 9 Groq models through Mastra's model router. Authentication is handled automatically using the `GROQ_API_KEY` environment variable.

Learn more in the [Groq documentation](https://console.groq.com/docs/models).

```bash
GROQ_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: "groq/llama-3.1-8b-instant"
});

// 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);
}
```

## Models

| Model                                                | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `groq/llama-3.1-8b-instant`                          | 131K    |       |           |       |       |       | $0.05      | $0.08       |
| `groq/llama-3.3-70b-versatile`                       | 131K    |       |           |       |       |       | $0.59      | $0.79       |
| `groq/meta-llama/llama-4-maverick-17b-128e-instruct` | 131K    |       |           |       |       |       | $0.20      | $0.60       |
| `groq/meta-llama/llama-4-scout-17b-16e-instruct`     | 131K    |       |           |       |       |       | $0.11      | $0.34       |
| `groq/meta-llama/llama-guard-4-12b`                  | 131K    |       |           |       |       |       | $0.20      | $0.20       |
| `groq/moonshotai/kimi-k2-instruct-0905`              | 262K    |       |           |       |       |       | $1         | $3          |
| `groq/openai/gpt-oss-120b`                           | 131K    |       |           |       |       |       | $0.15      | $0.60       |
| `groq/openai/gpt-oss-20b`                            | 131K    |       |           |       |       |       | $0.07      | $0.30       |
| `groq/qwen/qwen3-32b`                                | 131K    |       |           |       |       |       | $0.29      | $0.59       |

## Advanced Configuration

### Custom Headers

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.groq.com/openai/v1",
    id: "groq/llama-3.1-8b-instant",
    apiKey: process.env.GROQ_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
      ? "groq/qwen/qwen3-32b"
      : "groq/llama-3.1-8b-instant";
  }
});
```

## Direct Provider Installation

This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the [package documentation](https://www.npmjs.com/package/@ai-sdk/groq) for more details.

**npm**:

```bash
npm install @ai-sdk/groq
```

**pnpm**:

```bash
pnpm add @ai-sdk/groq
```

**Yarn**:

```bash
yarn add @ai-sdk/groq
```

**Bun**:

```bash
bun add @ai-sdk/groq
```

For detailed provider-specific documentation, see the [AI SDK Groq provider docs](https://ai-sdk.dev/providers/ai-sdk-providers/groq).