minimax/minimax-m2.7MiniMax-M2.7 is MiniMax’s open-weights AI model, released Mar 18, 2026. It scores 146 on the Epoch Capabilities Index, costs $0.60/M input and $1.80/M output tokens, and handles a 197K-token context window.
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
Scores on standardized evaluations. Higher is better — and rank shows where MiniMax-M2.7 lands among all models tracked on Model Beat.
Graduate-level scientific reasoning
Frontier of human expert knowledge
Novel ML problem-solving
Scientific research coding
Human-rated web development
Command-line agentic tasks
Tool-agent-user reliability
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
MiniMax-M2.7 is an AI model developed by MiniMax, part of the MiniMax family, released Mar 18, 2026.
MiniMax-M2.7 is served from $0.60 per million input tokens and $1.80 per million output tokens (cheapest credible provider on OpenRouter: Groq).
MiniMax-M2.7 supports a context window of up to 197K tokens.
On standardized evaluations tracked by Epoch AI, MiniMax-M2.7 scores 50.1% on SciCode, 29.6% on Humanity's Last Exam, 87.4% on GPQA Diamond.
MiniMax-M2.7 is released with open weights (Open weights (non-commercial)), so the model can be downloaded and self-hosted.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Nov 12, 2026.