GPT Realtime 2
OpenAI's most capable realtime voice model: a reasoning model with tool use, supporting speech-to-speech interactions with configurable reasoning effort and reliable tool use for complex voice-agent workflows.
text + audio → text + audio · made by OpenAI
$4→$24per Mtok in / out
Microsoft Azure AI · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | standard | $4per Mtok in$24per Mtok out$0.4per Mtok cached$0.4per Mtok cached, audio$0.5per Mtok cached, image$32per Mtok in, audio$5per Mtok in, image$64per Mtok out, audioraw.githubusercontent.com · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $4per Mtok in$24per Mtok out$0.4per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 7thof 16 | τ³-Voice Leaderboard | Pass^1 | 51.2 |
About
GPT Realtime 2 — a text and audio model from OpenAI, sold by 2 companies from $4 in and $24 out per million tokens, placed 7th of 16 on τ³-Voice Leaderboard.
It takes text and audio and returns text and audio, with a context window of 128,000 tokens. It was published in May 2026. The catalogue files it under speak. Two companies sell it. The cheapest is $4 in and $24 out per million tokens at Microsoft Azure AI. It stands 7th of 16 on τ³-Voice Leaderboard.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + audio
- Returns
- text + audio
- Context
- 128,000 tokens
- Published
- May 2026
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $4 in and $24 out per million tokens — Microsoft Azure AI
- Boards
- 1
- Best place
- 7th of 16 — τ³-Voice Leaderboard
Known as 2 names
gpt-realtime-2openai/gpt-realtime-2