Models / Xiaomi
MiMo-V2.5-Pro
by Xiaomi
Used for agents, coding, long documents, fast and frontier.
Best forCodingAgents and toolsLong documents
MiMo-V2.5-Pro is made by Xiaomi. It takes text, with a context window of 1M tokens. On Tīrtha it takes up to 262,144 tokens.
Price per 1M tokens
The live price, read from billing as this page loads. You pay only for the tokens you use, from prepaid credit.
catalog/mimo-v2.5-proTīrtha Bench review
What people use it for, in its maker's words:
Try it
Model id catalog/mimo-v2.5-pro · base URL https://api.tirtha.ai/v1. Any OpenAI-compatible client works: change the base URL and keep your code.
Using a coding tool? Set up OpenCode, Cline, Cursor and more. PowerShell and the full reference: Quickstart.
Limits and support
- Text inYes
- Context window1M tokensUp to 262,144 tokens on Tīrtha.
- StreamingYes
- Sampling settingsYou can set themThe maker publishes no default.
What it is for
- Coding
designed for the most demanding agentic, complex software engineering, and long-horizon tasks.
From the maker's card - Agents and tools
designed for the most demanding agentic, complex software engineering, and long-horizon tasks.
From the maker's card - Long documents
MiMo V2.5 Pro delivers a major leap in long-context reasoning.
From the maker's card
In the maker's own words, from its published model card. Claims and benchmarks on that card are the maker's own, not measured by Tīrtha.
What a job costs
1,000 calls of 2,000 tokens in and 500 out cost about -
Worked out from the live price above, without cached input. Your own calls will differ in size.
Similar models on Tīrtha
Licence
Weights: MIT. Read the licence.
From the maker: Model card: XiaomiMiMo/MiMo-V2.5-Pro on Hugging Face · Last updated by the maker: Oct 28, 2026Facts from the maker's card are the maker's own, not measured by Tīrtha.