GPT-4o Realtime
GPT-4o Realtime (model ID gpt-4o-realtime-preview) is a preview model capable of responding to audio and text inputs in realtime over WebRTC or a WebSocket interface.
text + audio → text + audio · made by OpenAI
$5.5→$22per Mtok in / out
Microsoft Azure AI
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | standard | $5.5per Mtok in$22per Mtok out$2.75per Mtok cached$20per Mtok cached, audio$44per Mtok in, audio$80per Mtok out, audioraw.githubusercontent.com · read 2026-09-16 |
About
GPT-4o Realtime — a text and audio model from OpenAI, sold by one company from $5.5 in and $22 out per million tokens.
It takes text and audio and returns text and audio, with a context window of 32,000 tokens. The catalogue files it under speak. Only Microsoft Azure AI sells it, at $5.5 in and $22 out per million tokens.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + audio
- Returns
- text + audio
- Context
- 32,000 tokens
- Licence
- not read
- Sellers
- 1
- Maker's own price
- not read
- Price
- $5.5 in and $22 out per million tokens — Microsoft Azure AI
Known as 1 name
gpt4o realtime