MiMo-V2.5

XiaomiMCP Tool CallReasoning

xiaomi/mimo-v2.5Open Weights

Open MiMo model for multimodal coding agents and long-context automation

Benchmark Pricing$0.14 / 1M in$0.28 / 1M out$0.00 cache read

Context: 1,048,576 tokens•Max Output: 131,072 tokens•Knowledge: 2024-12•Released: 2026-04-22

TECHNICAL SPECIFICATIONS

Context Window1,048,5761M tokens

Max Output131,072131.1K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVisionAudioVideo

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ MiMo-V2.5 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,048,576 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

MiMo Coding Benchscore

71.8

Claw-Evalscore

62.3

Terminal-Benchscore

65.8

SWE-Bench Proscore

56.1

CharXiv Reasoningscore

MMMU-Proscore

77.9

HR-Benchscore

88.5

OmniDocBenchscore

87.2

Claw-Evalscore

23.8

Video-MMEscore

87.7

DailyOmniscore

83.5

VideoHolmesscore

API CALL INVOCATION EXAMPLE

// Example: Calling MiMo-V2.5 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XIAOMI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "xiaomi/mimo-v2.5",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);