MiMo-V2.5-Pro
MiMo-V2.5-Pro is a large language model made by Xiaomi, added to the catalog on 22 Apr 2026. It has a context window of 262,144 tokens and costs $0.48 per 1M input tokens and $1.80 per 1M output tokens. It accepts text and produces text. Typical uses: complex software engineering, long-horizon text tasks and reasoning over text.
Price checked ยท source: OpenRouter
What MiMo-V2.5-Pro is
Xiaomi MiMo-V2.5-Pro is a text-in, text-out model from Xiaomi. Its stated areas of focus include general agentic capabilities, complex software engineering, and long-horizon tasks. It accepts text and produces text. The model has a context length of 262,144 tokens and a maximum output of 235,929 tokens, giving its text interactions a substantial stated capacity. These limits are useful details to consider when selecting it for work involving lengthy prompts or extended text responses.
The model supports reasoning, tools, structured outputs, and response formats. These features make it suited to tasks where a prompt calls for a reasoned text response, a defined output structure, or tool use. Its software engineering focus makes coding work a relevant use, while its stated focus on long-horizon tasks may suit work that unfolds across a larger body of text or multiple stages. The facts provided do not specify particular programming languages, tools, or output schemas, so those capabilities should be evaluated against the requirements of a given workflow. MiMo-V2.5-Pro is a text model, and the listed modalities do not include image or audio input or output. Its described focus and supported options can help determine whether it fits text-based reasoning, coding, or structured response tasks.
Key features
- Accepts text and produces text
- Has a context length of 262,144 tokens
- Supports reasoning and tool use
- Supports structured outputs and response formats
- Maximum output length is 235,929 tokens
Typical uses
- Complex software engineering
- Long-horizon text tasks
- Reasoning over text
- Generating structured responses
- Tool-supported text workflows
MiMo-V2.5-Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.48 |
| Output, per 1M tokens | $1.80 |
| Cached input read, per 1M tokens | $0.096 |
No price change since it was added on 22 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0008 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.013 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.018 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.075 |
MiMo-V2.5-Pro specifications
| Model id | xiaomi/mimo-v2.5-pro |
|---|---|
| Version | mimo-v2.5-pro-20260422 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 22 Apr 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for MiMo-V2.5-Pro yet.
Compare MiMo-V2.5-Pro
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.