o4 Mini
OpenAI · openai/o4-mini
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
o4 Mini ranks #273 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $2.75 blended per million tokens, it is cheaper than 26% of models with published API pricing. Its 200,000-token context window is 1.3× smaller than the catalog median (262,144 tokens).
Context
Max output: 100000
Pricing
Output / 1M: 4.40
Blend / 1M: 2.75
Quality
Provider
Moderated: yes
Monthly cost at this blended rate
Estimated API spend if every token is billed at $2.75per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $2.75 |
| 10,000,000 | $27.50 |
| 100,000,000 | $275.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from OpenAI
- GPT-5.5$17.50 / 1M · Q 81.8
- GPT-5.4$8.75 / 1M · Q 80.6
- GPT-5.2 Chat$7.88 / 1M · Q 76.4
- GPT-5.2$7.88 / 1M · Q 76.4
- GPT-5.1$5.63 / 1M · Q 76.1
Closest API price
- Muse Spark 1.3$2.75 / 1M
- Muse Spark 1.2$2.75 / 1M
- Muse Spark 1.1$2.75 / 1M
- o4 Mini High$2.75 / 1M
- o3 Mini High$2.75 / 1M