# GPT-Realtime mini

GPT-Realtime mini makes voice interfaces affordable at scale. You get realtime audio and text responses priced for features that run on every session, not just a demo.

- **Model ID:** `openai/gpt-realtime-mini`
- **Type:** realtime
- **Providers:** openai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $0.60/1M input tokens, $2.40/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-realtime-mini

## 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: 'openai/gpt-realtime-mini',
  });

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

## About

GPT-Realtime mini launched on October 10, 2025 at OpenAI's DevDay as the cost-efficient entry in the gpt-realtime family. GPT-Realtime mini responds to audio and text inputs in realtime, covering interactive voice use cases that don't need a flagship model on every turn.

The economics are the point. Voice features strain budgets when every session invokes a top-tier model. GPT-Realtime mini exists so in-app assistants, kiosks, and voice helpers can run continuously without the flagship rate, while keeping the low-latency conversational feel that makes voice interfaces usable.

Through AI Gateway, GPT-Realtime mini connects over WebSocket using the AI SDK's realtime hook. Your server mints a short-lived token, the browser handles microphone capture and playback through the hook, and AI Gateway applies the same observability and spend controls as your other models.

## What to consider

Realtime support on AI Gateway is in beta through AI SDK 7, connecting over WebSocket with a short-lived server-minted token. For agents that need heavier reasoning or complex tool chains, step up to `gpt-realtime-1.5` or `gpt-realtime-2`; the mini variant is tuned for cost and speed.

## When to use

### Best For

- High-volume voice features where per-session cost decides viability
- In-app voice assistants handling routine questions and commands
- Interactive prototypes and experiments that need realtime voice without flagship pricing
- Kiosks, devices, and embedded experiences running voice interaction continuously

### Consider Alternatives When

- Agents handle mission-critical support workflows; `gpt-realtime-1.5` is the flagship for voice agents
- Conversations involve multi-step reasoning or heavy tool use; `gpt-realtime-2` adds configurable reasoning effort
- You only need transcription or speech generation; `gpt-4o-mini-transcribe` and `tts-1` cost less per job

## Best for

- **High-volume voice features:** Per-session cost decides viability and the mini rate keeps features running
- **In-app voice assistants:** Routine questions and commands handled with realtime responses
- **Voice prototypes:** Realtime experiments without committing to flagship pricing
- **Always-on voice surfaces:** Kiosks, devices, and embedded experiences running continuous interaction

## Consider alternatives

- **Mission-critical voice agents:** `gpt-realtime-1.5` brings stronger instruction following and tool calling
- **Reasoning-heavy conversations:** `gpt-realtime-2` adds configurable reasoning effort for complex workflows
- **Single-direction audio jobs:** `gpt-4o-mini-transcribe` and `tts-1` handle transcription and speech generation directly

## Frequently asked questions

### How do I access GPT-Realtime mini through AI Gateway?

Realtime support is in beta through AI SDK 7. Mint a short-lived token on your server with the AI SDK's gateway provider, then connect from the browser with the AI SDK's realtime hook over WebSocket. The hook manages microphone capture and audio playback.

### What inputs does GPT-Realtime mini accept?

GPT-Realtime mini responds to both audio and text inputs in realtime, so a session can mix spoken conversation with typed messages or injected context.

### When should I upgrade from GPT-Realtime mini to gpt-realtime-1.5?

Upgrade when reliability on complex instructions and tool calls starts affecting outcomes. GPT-Realtime-1.5 is the flagship for customer support and mission-critical voice agents; the mini variant targets routine, high-volume interactions.

### Can GPT-Realtime mini call tools during a conversation?

Yes, realtime models on AI Gateway can invoke your tools mid-conversation. For workflows built around long tool chains and multi-step decisions, the larger gpt-realtime models are more reliable.

### How is GPT-Realtime mini priced?

Pricing is listed on this page. Rates reflect the providers routing through AI Gateway and update when providers change list prices.

### Does GPT-Realtime mini support zero data retention through AI Gateway?

Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

### What are typical latency characteristics?

This page shows live performance metrics measured across real AI Gateway traffic.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-realtime-mini)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)