o3-mini
Model ID
- Context
- 200K
- 100K max output
- Input price
- $1.10
- per 1M tokens · OpenAI API
- Output price
- $4.40
- per 1M tokens
- Epoch Capabilities Index
- 140.3
- #85 of 105 listed
- LMArena Text
- 1,364
- #120 of 149 listed
Where to run it
2 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
OpenAI API (opens in a new tab) o3-mini | ||
| Input | Standard | $1.10 / 1M tokens |
| Batch | $0.55 / 1M tokens | |
| Output | Standard | $4.40 / 1M tokens |
| Batch | $2.20 / 1M tokens | |
| Cache read | Standard | $0.55 / 1M tokens |
Azure OpenAI in Foundry (opens in a new tab) o3-mini-2025-01-31 | ||
| Input | Standard | $1.10 / 1M tokens |
| Batch | $0.55 / 1M tokens | |
| Output | Standard | $4.40 / 1M tokens |
| Batch | $2.20 / 1M tokens | |
| Cache read | Standard | $0.55 / 1M tokens |
Changes
All changes →No changes recorded yet.
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 140.3
#85 of 105 listed models · CI 137.4–141.9
- LMArena Text 1,364
#120 of 149 listed models · high effort · CI 1,358–1,369 · 18,589 votes
Also listed: o3-mini 1,348
- Epoch AI · FrontierMath Tiers 1–3 18.6%
#66 of 74 listed models · high effort · ±2.31
Also listed: medium effort 10.5% · low effort 3.9%
- Epoch AI · GPQA Diamond 77%
#72 of 128 listed models · high effort · ±2.59
Also listed: medium effort 74.3% · low effort 68.2%
- LMArena Text · Chinese 1,412
#108 of 149 listed models · high effort · CI 1,395–1,429 · 1,181 votes
Also listed: o3-mini 1,357
- LMArena Text · Coding 1,434
#108 of 149 listed models · high effort · CI 1,423–1,446 · 2,596 votes
Also listed: o3-mini 1,417
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 3, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 2, 2026
- changes we made