GPT-5 Mini
- Context
- 400K
- 128K max output
- Input price
- $0.25
- per 1M tokens · OpenAI API
- Output price
- $2.00
- per 1M tokens
- Epoch Capabilities Index
- 145.5
- #59 of 71 listed
- LMArena Text
- 1,390
- #71 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $0.25 / 1M tokens |
| Batch | $0.13 / 1M tokens | |
| Flex tier | $0.13 / 1M tokens | |
| Fast tier | $0.45 / 1M tokens | |
| Output | Standard | $2.00 / 1M tokens |
| Batch | $1.00 / 1M tokens | |
| Flex tier | $1.00 / 1M tokens | |
| Fast tier | $3.60 / 1M tokens | |
| Cache read | Standard | $0.025 / 1M tokens |
| Batch | $0.013 / 1M tokens | |
| Flex tier | $0.013 / 1M tokens | |
| Fast tier | $0.045 / 1M tokens | |
Azure OpenAI in Foundry (opens in a new tab) gpt-5-mini | ||
| Input | Standard | $0.25 / 1M tokens |
| Output | Standard | $2.00 / 1M tokens |
| Cache read | Standard | $0.030 / 1M tokens |
Azure OpenAI in Foundry (opens in a new tab) gpt-5-mini | ||
| Input | Standard | $0.28 / 1M tokens |
| Output | Standard | $2.20 / 1M tokens |
| Cache read | Standard | $0.030 / 1M tokens |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 145.5
#59 of 71 listed models · CI 143.5–147
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,390
#71 of 79 listed models · high effort · CI 1,385–1,394 · 26,641 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 46.7%
#39 of 56 listed models · high effort · ±2.96
Also listed: low effort 18.2% · minimal effort 6%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 75%
#58 of 64 listed models · high effort · ±2.28
Also listed: minimal effort 71.7% · medium effort 71.7%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · SWE-bench Verified 64.7%
#21 of 23 listed models · medium effort · ±2.17
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,404
#74 of 79 listed models · high effort · CI 1,390–1,419 · 1,920 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,431
#70 of 79 listed models · high effort · CI 1,423–1,440 · 5,480 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,202
#43 of 49 listed models · high effort · CI 1,194–1,210 · 28,970 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made