MiniMaxMiniMax-M3
- Released
- Jun 1, 2026
- Tracked since
- 2026-07-23
Intelligence index29.2Ranks 103 of 664 models with this metric
Coding index58.6Ranks 85 of 259 models with this metric
Agentic index29.5Ranks 64 of 156 models with this metric
Capability profile
5 axes vs. site averageMiniMax-M3
Site average
Pricing
per 1M tokens- Input
- $0.300
- Output
- $1.20
- Cache read
- $0.060
- Cache write
- $0.380
Performance
- Output throughput
- 179 tokens/sec
- Time to first token
- 1.07s
- First answer token
- 12.22s
- End-to-end response
- 15.00s
History
6Intelligence index
44.4→29.2
Output
Unchanged across 62 days of records
Output throughput
105→179
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−61% - GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−58% - GPT-6 Luna (max)
OpenAIIntelligence 37.3$0.500−58% - GPT-6 Luna (xhigh)OpenAIIntelligence 33.9$0.500−58%
- GPT-6 Luna (high)OpenAIIntelligence 32.1$0.500−58%