Realtime voice model
gpt-realtime pricing
OpenAI charges $4.00 per million input tokens and $16.00 per million output tokens for gpt-realtime, and $0.40 for cached input, with audio at $32.00 in and $64.00 out. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $4.00/ 1M
- Output
- $16.00/ 1M
- Cached input
- $0.40/ 1M
- Audio input
- $32.00/ 1M
Retires 2027-01-20. Move to a current realtime / audio model. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $4.00 | $16.00 | $0.40 | — |
USD per million tokens. Audio output costs $64.00. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Cost |
|---|
Planning a mix of models? Simulate a workload with gpt-realtime, alongside anything else you run.
Price history
No price changes since Veqen started tracking this model.
Also billed under: gpt-realtime-2025-08-28.
Compare
Last verified with price book 2026-10-22. Sources: OpenAI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.