MiMo-V2.5-Pro is the latest flagship model released by Xiaomi. Compared to its predecessor, it delivers significant improvements in general agentic capabilities, complex software engineering, and long-horizon tasks, ranking top on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and fully autonomously complete professional tasks that would take human experts days or even weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it ideally suited for integration with various agent frameworks.
| Model | Context | Max out | Pricing |
|---|---|---|---|
| MiMo V2 Omni Free | — | — | — |
| MiMo V2 Pro Free | — | — | — |
| MiMo-V2.5 Free | — | — | — |
| MiMo-V2.5-Pro | 1.0M | 131K | — |
| MiMo-V2.5 | 1.0M | 131K | — |
| MiMo-V2.6-Flash Free | — | — | $0$0 |
| MiMo-V2.6-Flash | 1.0M | 131K | — |
| MiMo-V2.6-Pro | 1.0M | 131K | — |
/v1/models/opencode/mimo-v2.5-proMiMo-V2.5-Pro is the latest flagship model released by Xiaomi. Compared to its predecessor, it delivers significant improvements in general agentic capabilities, complex software engineering, and long-horizon tasks, ranking top on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and fully autonomously complete professional tasks that would take human experts days or even weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it ideally suited for integration with various agent frameworks.