MiMo-V2.5-Pro is purpose-built to push the boundaries of complex software engineering and extreme long-horizon tasks. Compared to its predecessor, it achieves a comprehensive leap in general agentic capabilities, advancing the human-AI collaboration paradigm toward true "autonomous delivery." Without human intervention, it stably orchestrates massive workflows requiring up to a thousand tool calls in a single session, not only precisely capturing implicit requirements within ultra-long contexts but also demonstrating exceptional global architectural planning and self-correction discipline. In core agentic scenarios and long-horizon complexities, MiMo-V2.5-Pro is fully equipped to go head-to-head with top-tier global models like Claude Opus 4.6 and GPT-5.4. Backed by this exceptionally high execution confidence and long-term logical consistency, it completely sheds the "co-pilot" label, ready to take on truly serious, professional-grade workloads in real-world business environments.
| Input | $2 per million tokens |
| Cached reads | $0.4 per million tokens |
| Output | $6/百万 tokens |
Tiered pricing
| Request the length each time | Input | Cached reads | Selling price |
|---|
| 0 < tokens <= 262,144 | $1 | $0.2 | $3 |
| 262,144 < tokens <= 1,048,576 | $2 | $0.4 | $6 |