Model prices / OpenAI / GPT-Realtime-2.1
GPT-Realtime-2.1
OpenAI · released 2026-07-06
The official API price of GPT-Realtime-2.1 is $4 per 1M input tokens and $24 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 32K output tokens per request. 2 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| OpenAIOfficialgpt-realtime-2.1 | $4 | $24 | $0.4 | Official | Official docs |
 Vercel AI Gatewayopenai/ | $4 | $24 | $0.4 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
Description from models.dev.
Specs
- Type
- Realtime
- Context
- 128K
- Max output
- 32K
- Input
- Text, Audio, Image
- Output
- Text, Audio
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- No
- Knowledge cutoff
- 2024-09-30
- Open weights
- No
- Released
- 2026-07-06
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.