MiniMaxMiniMax-M2.5
- Released
- Feb 12, 2026
- Tracked since
- 2026-07-23
Intelligence index22.8Ranks 172 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageMiniMax-M2.5
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.300
- Output
- $1.20
- Cache read
- $0.030
- Cache write
- $0.380
Performance
- Output throughput
- 100 tokens/sec
- Time to first token
- 1.46s
- First answer token
- 21.54s
- End-to-end response
- 26.56s
History
2Intelligence index
33.7→22.8
Output
Unchanged across 62 days of records
Output throughput
85→100
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−83% - Ling 3.0 Flash
InclusionAIIntelligence 24.9$0.220−82% - Ling-3.0-flash-VLInclusionAIIntelligence 24.6$0.220−82%
- Ling-3.0-flash-FinInclusionAIIntelligence 22.6$0.220−82%
- DeepSeek V4 Flash 0420 (Reasoning, High Effort)
DeepSeekIntelligence 26$0.280−77%