# GPT-Live 1

Our premier model for natural, expressive voice conversations with smooth interruption handling.

- **Model ID:** `openai/gpt-live-1`
- **Type:** realtime
- **Providers:** openai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-live-1

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { createOpenAI } from '@ai-sdk/openai';
import WebSocket from 'ws';

// Server-side setup using @ai-sdk/openai 4.0.67 or later.
const apiKey = process.env.AI_GATEWAY_API_KEY;
if (!apiKey) throw new Error('Set AI_GATEWAY_API_KEY');

const live = createOpenAI({
  apiKey,
  baseURL: 'https://ai-gateway.vercel.sh/v1',
}).experimental_realtime('openai/gpt-live-1', { api: 'live' });

const { url, headers } = live.getServerWebSocketConfig();
const ws = new WebSocket(url, { headers });

ws.on('open', () => {
  ws.send(JSON.stringify(live.serializeClientEvent({
    type: 'session-start',
    config: {
      providerOptions: {
        openai: { store: false, delegation: { type: 'client' } },
      },
    },
  })));
});

// Wait for session.started before streaming paced PCM audio.
// Complete audio/close example: vercel.com/docs/ai-gateway/modalities/realtime/gpt-live
```

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-live-1)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://developers.openai.com/api/docs/models/gpt-live-1)