# Gemini 3.8 Live Extended Thinking

Gemini 3.8 Live Extended Thinking is Google's real-time audio model with extended thinking capabilities. It combines spoken interaction with additional reasoning for voice assistants and other conversational applications.

- **Model ID:** `google/gemini-3.8-live-extended-thinking`
- **Type:** realtime
- **Providers:** google
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $0.75/1M input tokens, $4.5/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gemini-3.8-live-extended-thinking

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { gateway } from '@ai-sdk/gateway';

export async function POST() {
  const { token, url } = await gateway.experimental_realtime.getToken({
    model: 'google/gemini-3.8-live-extended-thinking',
  });

  return Response.json({ token, url, tools: [] });
}
```

## Links

- [Model page](https://vercel.com/ai-gateway/models/gemini-3.8-live-extended-thinking)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider pricing](https://ai.google.dev/gemini-api/docs/pricing)