Minimax 2.5
About this model
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
Performance Tier
Minimax 2.5 is a balanced model from Minimax : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.120 |
| Output (completion) | $1.00 |
| Cache read | $0.060 |
Capabilities
Benchmarks
Recommended Use Cases
Strengths
- Top-tier software engineering (SWE-bench 80.2%, rivaling Claude Opus)
- Extremely cost-efficient — frontier coding at $0.30/$1.20 per M tokens
- Fast inference at 100 TPS with 205K context window
- Open-weight MoE model enabling self-hosting
Limitations
- Weaker on general reasoning and math than top proprietary models
- Smaller community and ecosystem compared to Claude/GPT/Gemini
- Creative writing and conversational fluency lag behind chat-optimized models
Resources
This model may use your data for training
