Intelligence Index
0132.1
> 53% OF MODELS
Minimax
MiniMax M2.1
Updated: August 2026
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
Specifications
- Context
- 205K
- Input Modalities
- Text
- Output Modalities
- Text
- Input
- $0.3/M
- Output
- $1.2/M
Capabilities
TEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Gemini 3.5 Flash Lite | Google | 1M | $0.3/M | $2.5/M |
| Gemini 3.5 Flash Lite | Google | 1M | $0.3/M | $2.5/M |
| Qwen3.5 Plus 2026-04-20 | Qwen | 1M | $0.3/M | $1.8/M |
| Minimax M2.7 | Minimax | 205K | $0.3/M | $1.2/M |
| Minimax M2.7 | Minimax | 205K | $0.3/M | $1.2/M |
Performance Metrics
Average Response Performance
- Output Speed
- 84.6 tok/s
- Time To First Token
- 1.74s
- Time To First Answer Token
- 25.37s
- End To End Response Time
- 31.28s
DATA SOURCE: Artificial Analysis