OpenAI: gpt-realtime-2
gpt-realtime-2 is a language model from OpenAI released on May 7, 2026. It reads text and audio and writes text and audio.
Show moreShow less
It costs $4 per million input tokens and $24 per million output tokens. Cached input bills at $0.40, 90% less than fresh input.
It supports prompt caching.
- Modalities
- In / out price
- $4 / $24 per 1M
- Context
- n/a
- Max output
- n/a
- Released
- May 7, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
gpt-realtime-2 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $4 / 1M tokens | |
|---|---|---|
| Output | $24 / 1M tokens | |
| Cached input (read) | $0.40 / 1M tokens | 90% off input |
What gpt-realtime-2 costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call gpt-realtime-2 through an OpenAI compatible API.
- Temperature
temperature
Alternatives to gpt-realtime-2
Models that take the same inputs, closest in price, cheaper ones first.
- 128K context
Reads text, images and audio, writes text and audio. Tool calling, reasoning. Served by 2 providers.
by openaiJul 6, 2026$4/M input tokens$24/M output tokens2 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by metaOct 12, 2026$4/M input tokens$20/M output tokens7 providers
- 32K context
Reads text and audio, writes text and audio. Tool calling. Served by 2 providers.
by openaiJun 1, 2025$4/M input tokens$16/M output tokens2 providers
- Index 29.7
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 5 providers.
by googleFeb 19, 20261.05M context$2/M input tokens$12/M output tokens5 providers
- 1.05M context
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 8 providers.
by xiaomiSep 21, 2026$4.35/M input tokens$8.70/M output tokens8 providers
- Index 14.2
Reads text, images, audio and video. Reasoning.
by amazonDec 2, 20251M context$1.25/M input tokens$10/M output tokens
More from OpenAI
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 29, 2026$2/M input tokens$10/M output tokens2 providers
- Index 38.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 20261.05M context$0.10/M input tokens$0.50/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$0.10/M input tokens$0.50/M output tokens2 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens2 providers
gpt-realtime-2 questions
How much does the gpt-realtime-2 API cost?
$4 per million input tokens and $24 per million output tokens, with cached input at $0.40. The estimator on this page turns that into a monthly bill for your own workload.
Does gpt-realtime-2 support tool calling?
Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.
Is gpt-realtime-2 open source?
No. OpenAI serves it through an API only, so you cannot download the weights or host it yourself.
When was gpt-realtime-2 released?
May 7, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on gpt-realtime-2?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting