gpt-realtime-2
OpenAI · released 2026-05-07
No price from the maker itself is on record for gpt-realtime-2. The lowest of 1 providers is Vercel AI Gateway: $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.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Vercel AI GatewayLowestopenai/ | $4 | $24 | $0.4 | Lowest | 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 and reliable tool use for voice agents
Description from models.dev.
Specs
- Type
- Realtime
- Context
- 128K
- Max output
- 32K
- Input
- Text, Audio
- Output
- Text, Audio
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- —
- Knowledge cutoff
- 2024-09-30
- Open weights
- No
- Released
- 2026-05-07
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.