# 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.
Prices as of 2026-10-04.

| 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

## FAQ

### What is the cheapest GPT-Realtime-2.1 API?

As of Oct 4, 2026, OpenAI has the lowest GPT-Realtime-2.1 output price at $24 per 1M tokens, and OpenAI has the lowest input price at $4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-Realtime-2.1 cost on OpenAI?

OpenAI charges $4 per 1M input tokens and $24 per 1M output tokens for GPT-Realtime-2.1.

### How many providers offer GPT-Realtime-2.1?

2 providers list GPT-Realtime-2.1 on Sovyron; 2 of them sell it at a metered per-token price.

### Is GPT-Realtime-2.1 free?

No provider in the Sovyron catalog lists a free tier for GPT-Realtime-2.1.

### What is the context window of GPT-Realtime-2.1?

GPT-Realtime-2.1 supports a 128k-token context window and up to 32k output tokens.

HTML page: https://sovyron.com/models/gpt-realtime-2-1/
Full dataset: https://sovyron.com/data/catalog.json