OpenAI: gpt-realtime-2
Realtime speech-to-speech model with configurable reasoning and reliable tool use for voice agents
Cheapest input
$4
$/MTok · models.dev
Cheapest output
$24
$/MTok
Context
128K
tokens
Sources
2
3 listings
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $16 → $24
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestopenai/gpt-realtime-2 | Vercel AI Gateway | $4 | $24 | $0.4 | 128K |
| LiteLLMazure/gpt-realtime-2 | N/A | $4 | $24 | $0.4 | N/A |
| LiteLLMgpt-realtime-2 | N/A | $4 | $24 | $0.4 | N/A |
Capabilities
- Tool calling
- Attachments
- In: text
- In: audio
- Out: text
- Out: audio
Knowledge cutoff: 2024-09-30Released: 2026-05-07Family: gpt
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.