CrossModel
MiMo V2.5 Pro
xiaomi/mimo-v2.5-pro
Back to model catalog

Xiaomi · Model guide

MiMo V2.5 Pro

Compare
xiaomi/mimo-v2.5-pro

Xiaomi's strongest open-weight MiMo model, a 1.02T-parameter sparse MoE with 42B active parameters and a 1M-token context. It is optimized for demanding coding, long-horizon agents and trajectories spanning thousands of tool calls.

Modalities
TextText
Context
1M
Max output
128K
Price / 1M tokens
$ 0.47in$ 0.94out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorXiaomi's most capable model for demanding agentic and complex software-engineering tasks.source

Best for

  • Long-horizon coding agents · Designed to sustain coherent trajectories across thousands of tool calls.(vendor claim)source

  • Long-context reasoning · GraphWalks results remain non-zero at the full 1M-token span.(vendor claim)source

Neighbouring models
  • xiaomi/mimo-v2.5sibling —Choose the omnimodal model when image understanding matters.
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 0.47
Output$ 0.94
Cache read$ 0.0050
Cache write$ 0.47
Estimate a request
$ 0.0066
Estimated cost per request
10.0K × $ 0.47
+ 2.0K × $ 0.94
≈ $ 6.58 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
128.0K tokens
Input / output modalities
Text → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Not supported
Thinking mode
Supported· can be turned off
Reasoning effort
none · low · medium · high
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specshuggingface.co 1mimo.mi.com 2Capabilitiesmimo.mi.com 1mimo.mi.com 2mimo.mi.com 3

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Coding
  • SWE-Bench Pro
    resolved_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    57.2%
  • SWE-Bench Verified
    resolved_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    78.9%
Long context
  • GraphWalks BFS at 1M
    score·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    0.37
  • GraphWalks BFS at 512K
    score·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    0.56
  • GraphWalks Parents at 1M
    score·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    0.62
  • GraphWalks Parents at 512K
    score·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    0.92

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is MiMo V2.5 Pro?
MiMo V2.5 Pro is available on CrossModel as xiaomi/mimo-v2.5-pro. It has a 1M-token context window and can return up to 128K tokens per request.
How much does MiMo V2.5 Pro cost?
Currently $ 0.47 per 1M input tokens and $ 0.94 per 1M output tokens. Cached input is billed at $ 0.0050 per 1M.
Does MiMo V2.5 Pro support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Not supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.