MiniMax: MiniMax M2.5
Analysis Summary
MiniMax M2.5 is a text-only model from MiniMax with an intelligence index matching Qwen3.5 397B A17B but without a published coding index. Its agentic score of 65.1 is competitive, and it supports tool use and function calling, making it viable for structured automation tasks.
For businesses, it fits well in high-volume agentic pipelines, content generation, and instruction-following workflows where vision is not required. The absence of a coding index and vision support limits its versatility compared to multimodal peers at a similar intelligence level. Long-context reasoning scores are reasonable for document-level tasks within its 204K window.
At $0.12 input and $0.48 output per million tokens, it is among the more cost-efficient options in its capability tier. Teams prioritising volume and cost over breadth will find it a practical fit, though a -4 point regional penalty applies for provider accessibility.
Assessed June 30, 2026
Editorial notes
MiniMax M2.5 delivers strong agentic performance and competitive instruction following at very low cost, though it lacks vision support and a coding index score.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MiniMax: MiniMax M2.5 compares
MiniMax: MiniMax M2.5 ranks #57 of 385 AI models we track for overall intelligence, #41 of 293 for agentic tasks. Its 205K-token context window is larger than 67% of the models we list. At $0.12 per million input tokens it is cheaper than 61% of comparable models.
About MiniMax: MiniMax M2.5
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..
Capabilities
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MiniMax: MiniMax M2.5 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
minimax/minimax-m2.5
|
| Provider | minimax |
| Release Date | February 12, 2026 |
| Context Length | 204,800 tokens |
| Max Completion | 196,608 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.12 | $0.000120 |
| Output | $0.48 | $0.000480 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about MiniMax: MiniMax M2.5
How much does MiniMax: MiniMax M2.5 cost?
MiniMax: MiniMax M2.5 costs $0.12 per million input tokens and $0.48 per million output tokens.
What is the context window of MiniMax: MiniMax M2.5?
MiniMax: MiniMax M2.5 has a context window of 204,800 tokens (205K).
What can MiniMax: MiniMax M2.5 do?
MiniMax: MiniMax M2.5 supports tool use and function calling.
Who created MiniMax: MiniMax M2.5?
MiniMax: MiniMax M2.5 is developed by MiniMax and was released on February 12, 2026.
