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

Xiaomi · Model guide

MiMo V2.5

Compare
xiaomi/mimo-v2.5

Xiaomi's open-weight native omnimodal MiMo model, built on a 310B sparse MoE with 15B active parameters and a 1M-token context. It combines image understanding with reasoning, coding and tool-driven agent workflows; the open weights also support video and audio understanding.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 0.16in$ 0.32out
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.

VendorA native omnimodal model with strong agentic capabilities.source

Best for

  • Omnimodal understanding · The native architecture combines text, vision, video and audio encoders.(vendor claim)source

  • Coding agents · Post-training explicitly targets coding, tool use and long agent trajectories.(vendor claim)source

Neighbouring models
  • xiaomi/mimo-v2.5-prostronger —Choose Pro for the most demanding software-engineering and long-horizon agent tasks.
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$ 0.16
Output$ 0.32
Cache read$ 0.0040
Cache write$ 0.16
Estimate a request
$ 0.0022
Estimated cost per request
10.0K × $ 0.16
+ 2.0K × $ 0.32
≈ $ 2.24 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 + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
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.

Agentic coding
  • Terminal-Bench 2.0
    pass_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    65.8%
Agentic tasks
  • Claw-Eval General
    pass3_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed

    161 tasks, Pass³ metric with N=3.

    62.1%
  • Claw-Eval Multi Turn
    pass3_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed

    38 tasks, Pass³ metric with N=3.

    63.2%
Coding
  • SWE-Bench Pro
    resolved_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed
    56.1%
Multimodal
  • Claw-Eval Multimodal
    pass3_rate·Xiaomi MiMo · 2026-04-27setup not fully disclosed

    101 tasks, Pass³ metric with N=3.

    23.8%

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?
MiMo V2.5 is available on CrossModel as xiaomi/mimo-v2.5. It has a 1M-token context window and can return up to 128K tokens per request.
How much does MiMo V2.5 cost?
Currently $ 0.16 per 1M input tokens and $ 0.32 per 1M output tokens. Cached input is billed at $ 0.0040 per 1M.
Does MiMo V2.5 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: 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.