# GPT-Realtime-2.1 API prices

GPT-Realtime-2.1 (gpt) — 128k context, 32k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenAI | $4 | $24 | $0.4 | 128k |
| Vercel AI Gateway | $4 | $24 | $0.4 | 128k |

## Summary

- Cheapest input: $4 per 1M tokens (OpenAI)
- Cheapest output: $24 per 1M tokens (OpenAI)
- First-party: $24 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-07-06
- Inputs: audio, image, text

HTML page: https://llmprice.gitlab.io/models/gpt-realtime-2-1/
Full dataset: https://llmprice.gitlab.io/data/catalog.json