Intelligence Index
0145.4
> 79% OF MODELS
Minimax
Minimax M3
Updated: September 2026
Multimodal 1M-context model for long-horizon agentic work, coding, and tool use.
Specifications
- Context
- 1M
- Input Modalities
- Image, Text, File
- Output Modalities
- Text
- Input
- $0.6/M
- Output
- $2.4/M
Capabilities
VISIONTHINKINGCODINGWEB
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| GPT Audio Mini | OpenAI | 128K | $0.6/M | $2.4/M |
| Z.ai: GLM 4.5V | Z-AI | 66K | $0.6/M | $1.8/M |
| Gemini 2.5 Pro (batch) | Google | 1M | $0.625/M | $5/M |
| Qwen3.5 397B A17B | Qwen | 262K | $0.55/M | $3.5/M |
| GLM 4.5 | Z-AI | 131K | $0.55/M | $2/M |
Performance Metrics
Coding Index
0258.6
> 67% OF MODELS
Agentic Index
0336.1
> 70% OF MODELS
Average Response Performance
- Output Speed
- 131.1 tok/s
- Time To First Token
- 1.23s
- Time To First Answer Token
- 16.48s
- End To End Response Time
- 20.3s
DATA SOURCE: Artificial Analysis