# ![Neon logo](https://models.dev/logos/neon.svg)Neon

Access 25 Neon models through Mastra's model router. Authentication is handled automatically using the `NEON_AI_GATEWAY_TOKEN` environment variable. Configure `NEON_AI_GATEWAY_BASE_URL` as well.

Learn more in the [Neon documentation](https://neon.com/docs).

```bash
NEON_AI_GATEWAY_BASE_URL=your-value
NEON_AI_GATEWAY_TOKEN=your-api-token
```

```typescript
import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "neon/claude-haiku-4-5"
});

// 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 [Neon documentation](https://neon.com/docs) for details.

## Models

| Model                        | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| ---------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `neon/claude-haiku-4-5`      | 200K    |       |           |       |       |       | $1         | $5          |
| `neon/claude-opus-4-1`       | 200K    |       |           |       |       |       | $15        | $75         |
| `neon/claude-opus-4-5`       | 200K    |       |           |       |       |       | $5         | $25         |
| `neon/claude-opus-4-6`       | 1.0M    |       |           |       |       |       | $5         | $25         |
| `neon/claude-opus-4-7`       | 1.0M    |       |           |       |       |       | $5         | $25         |
| `neon/claude-sonnet-4`       | 200K    |       |           |       |       |       | $3         | $15         |
| `neon/claude-sonnet-4-5`     | 200K    |       |           |       |       |       | $3         | $15         |
| `neon/claude-sonnet-4-6`     | 1.0M    |       |           |       |       |       | $3         | $15         |
| `neon/gemini-2-5-flash`      | 1.0M    |       |           |       |       |       | $0.30      | $3          |
| `neon/gemini-2-5-pro`        | 1.0M    |       |           |       |       |       | $1         | $10         |
| `neon/gemini-3-1-flash-lite` | 1.0M    |       |           |       |       |       | $0.25      | $2          |
| `neon/gemini-3-1-pro`        | 1.0M    |       |           |       |       |       | $2         | $12         |
| `neon/gemini-3-flash`        | 1.0M    |       |           |       |       |       | $0.50      | $3          |
| `neon/gemini-3-pro`          | 1.0M    |       |           |       |       |       | $2         | $12         |
| `neon/gpt-5`                 | 400K    |       |           |       |       |       | $1         | $10         |
| `neon/gpt-5-1`               | 400K    |       |           |       |       |       | $1         | $10         |
| `neon/gpt-5-2`               | 400K    |       |           |       |       |       | $2         | $14         |
| `neon/gpt-5-4`               | 1.1M    |       |           |       |       |       | $3         | $15         |
| `neon/gpt-5-4-mini`          | 400K    |       |           |       |       |       | $0.75      | $5          |
| `neon/gpt-5-4-nano`          | 400K    |       |           |       |       |       | $0.20      | $1          |
| `neon/gpt-5-5`               | 1.1M    |       |           |       |       |       | $5         | $30         |
| `neon/gpt-5-mini`            | 400K    |       |           |       |       |       | $0.25      | $2          |
| `neon/gpt-5-nano`            | 400K    |       |           |       |       |       | $0.05      | $0.40       |
| `neon/gpt-oss-120b`          | 131K    |       |           |       |       |       | $0.07      | $0.28       |
| `neon/gpt-oss-20b`           | 131K    |       |           |       |       |       | $0.05      | $0.20       |

## Advanced configuration

### Custom headers

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1",
    id: "neon/claude-haiku-4-5",
    apiKey: process.env.NEON_AI_GATEWAY_TOKEN,
    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
      ? "neon/gpt-oss-20b"
      : "neon/claude-haiku-4-5";
  }
});
```