MiniMax-M3
- Context
- 1M
- 512K max output
- Input price
- $0.30
- per 1M tokens · MiniMax API
- Output price
- $1.20
- per 1M tokens
- Epoch Capabilities Index
- 147
- #50 of 71 listed
- LMArena Text
- 1,441
- #51 of 79 listed
Where to run it
2 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $0.30 / 1M tokens |
| Priority tier | $0.45 / 1M tokens | |
| Prompts over 512K tokens | $0.60 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | $0.90 / 1M tokens | |
| Output | Standard | $1.20 / 1M tokens |
| Priority tier | $1.80 / 1M tokens | |
| Prompts over 512K tokens | $2.40 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | $3.60 / 1M tokens | |
| Cache read | Standard | $0.060 / 1M tokens |
| Priority tier | $0.090 / 1M tokens | |
| Prompts over 512K tokens | $0.12 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | $0.18 / 1M tokens | |
| Input | Standard | ¥2.10 / 1M tokens |
| Priority tier | ¥3.15 / 1M tokens | |
| Prompts over 512K tokens | ¥4.20 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | ¥6.30 / 1M tokens | |
| Output | Standard | ¥8.40 / 1M tokens |
| Priority tier | ¥12.60 / 1M tokens | |
| Prompts over 512K tokens | ¥16.80 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | ¥25.20 / 1M tokens | |
| Cache read | Standard | ¥0.42 / 1M tokens |
| Priority tier | ¥0.63 / 1M tokens | |
| Prompts over 512K tokens | ¥0.84 / 1M tokens | |
| Prompts over 512K tokens · Priority tier | ¥1.26 / 1M tokens | |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 147
#50 of 71 listed models · CI 142.9–149.7
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
- LMArena Text 1,441
#51 of 79 listed models · CI 1,437–1,445 · 56,646 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · GPQA Diamond 90.9%
#22 of 64 listed models · ±2.05
Also listed: reasoning off 81.3%
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 1,473
#55 of 79 listed models · CI 1,463–1,484 · 3,518 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 1,495
#45 of 79 listed models · CI 1,489–1,501 · 16,426 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,254
#33 of 49 listed models · CI 1,247–1,261 · 15,192 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made