OpenAI: o3 Mini
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
Everything else
| Max output | 100K |
|---|---|
| Input / 1M | $1.10 |
| Output / 1M | $4.40 |
| Cache read / 1M | $0.55 |
| Cache write / 1M | — |
| 1M in + 1M out | $5.50 |
| Takes | text, file |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | no |
| Released | 2025-01-31 |
| Knowledge cutoff | 2023-10-31 |
| Retires | — |
| Catalog id | openai/o3-mini |
Benchmarks
| source | epoch |
|---|---|
| eci | 141.42 |
| confidence | Unknown |
| accessibility | API access |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.