Minimax 2.7
MinimaxFlagship
ThinkingTool UseStructured Output
About this model
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
Performance Tier
Flagship
Minimax 2.7 is a flagship model from Minimax : the most capable in their lineup.
Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.
Pricing
This model is included in Elosia plansAffordable
Low cost. Suitable for sustained use and high-volume interactions.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.279 |
| Output (completion) | $1.20 |
Capabilities
Context Length197K
Max Output Tokens131K
TokenizerOther
Inputtext
Outputtext
Release DateMarch 18, 2026
Benchmarks
General Intelligence
MMLU
Not reported
GPQA Diamond
Not reported
Mathematics
MATH-500
Not reported
Programming
HumanEval
Not reported
SWE-bench Verified
Not reported
Reasoning
IFEval
Not reported
Agentic
SWE-bench Pro
56.2%
Terminal-Bench 2.0
57%
VIBE-Pro
55.6%
Multi SWE Bench
52.7%
Recommended Use Cases
CodingAnalysisResearchData Extraction
Strengths
- Industry-leading agentic coding (SWE-Pro 56.2%, Terminal-Bench 57.0%)
- Full project delivery capability (VIBE-Pro 55.6%)
- Self-evolving model with autonomous research workflow capabilities
- Extremely cost-efficient at $0.30/$1.20 per M tokens with 205K context
Limitations
- No standard academic benchmarks published (MMLU, GPQA, MATH)
- Text-only — no multimodal support
- Smaller community and ecosystem compared to Claude/GPT/Gemini
Resources
This model may use your data for training
