gpt-realtime-2.1-mini pricing
gpt-realtime-2.1-mini from OpenAI costs $10.00 per 1M input tokens and not published per 1M output tokens. Cached input is $0.300 per 1M.
API id gpt-realtime-2.1-mini · OpenAI · source · updated 2026-08-11
$10.00
Input / 1M tokens
—
Output / 1M tokens
$0.300
Cached input / 1M
—
Context window
What gpt-realtime-2.1-mini costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.01 |
| Document summary | 50,000 | 2,000 | $0.50 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $10.00 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does gpt-realtime-2.1-mini cost per 1M tokens?
- gpt-realtime-2.1-mini costs $10.00 per 1M input tokens and not published per 1M output tokens on the standard tier. Cached input is $0.300 per 1M.
- What is gpt-realtime-2.1-mini's context window?
- OpenAI does not publish a context window for gpt-realtime-2.1-mini on its pricing page.
- Is there a cheaper OpenAI model than gpt-realtime-2.1-mini?
- Yes. gpt-4o-mini-2024-07-18 is $0.300 per 1M input tokens versus $10.00 for gpt-realtime-2.1-mini, with a 128,000 token context window.
- Where does this gpt-realtime-2.1-mini price come from?
- Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.