gpt-realtime pricing
gpt-realtime from OpenAI costs $4.00 per 1M input tokens and $16.00 per 1M output tokens. Cached input is $0.400 per 1M.
API id gpt-realtime · OpenAI · source · updated 2026-09-25
We have not confirmed what kind of model this is. Its name suggests one thing and its pricing another, and we would rather say so than guess.
$4.00
Input / 1M tokens
$16.00
Output / 1M tokens
$0.400
Cached input / 1M
—
Context window
gpt-realtime specifications
- Provider
- OpenAI
- API id
gpt-realtime- Model type
- unknown
- Context window
- — tokens
- Max output
- not published
- Currency
- USD
- Price source
- First-party
- Last checked
- 2026-09-25
Tags
- audio
What gpt-realtime costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.01 |
| Document summary | 50,000 | 2,000 | $0.23 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $7.20 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
gpt-realtime price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-08-25 | $4.00 | $16.00 |
| 2026-08-23 | $32.00 | — |
| 2026-08-22 | $4.00 | — |
Common questions
- How much does gpt-realtime cost per 1M tokens?
- gpt-realtime costs $4.00 per 1M input tokens and $16.00 per 1M output tokens on the standard tier. Cached input is $0.400 per 1M.
- What is gpt-realtime's context window?
- OpenAI does not publish a context window for gpt-realtime on its pricing page.
- Is there a cheaper OpenAI model than gpt-realtime?
- Yes. omni-moderation-latest is free per 1M input tokens versus $4.00 for gpt-realtime.
- Where does this gpt-realtime price come from?
- Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.