OpenAICodex Mini
Not yet ranked: too few independent results so far. Released 16 May 2025.
- Blended price
- $2.63/M
- $1.50 in · $6.00 out
- Output speed
- –
- First answer
- –
- Context
- 200k
- Reasoning35
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.375 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0024 | $0.0021 | – |
| Summarise a 30-page report | 12,000 / 600 | $0.022 | $0.011 | – |
| Code edit | 6,000 / 1,500 | $0.018 | $0.013 | – |
| Agentic coding session | 60,000 / 4,000 | $0.114 | $0.063 | – |
| Structured extraction | 2,000 / 200 | $0.0042 | $0.0025 | – |
See also
Data as of 9 Sept 2026. Compare with another model.