MiMo-V2.5-Pro

XiaomiMCP Tool CallReasoning
xiaomi/mimo-v2.5-proOpen Weights

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Benchmark Pricing$0.43 / 1M in$0.87 / 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
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ MiMo-V2.5-Pro 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

SWE-Bench Verifiedresolved
78.9
SWE-Bench Proresolve rate
57.2
GPQA Diamondaccuracy
86.6
DeepSWEscore
19
ProgramBenchscore
12.5
MiMo Code Benchscore
40.4
AutomationBenchscore
16
Toolathlon-Verifiedscore
49.1
GDPval-AAElo
1107
Agents' Last Examscore
13.2
Terminal-Benchscore
1.5
Terminal-Benchscore
65.2
JobBenchscore
25
CyberGymscore
40
MiMo Cyber Benchscore
0
ExploitGymscore
0.2
ExploitBenchscore
16.6
SEC-Bench Proscore
17.7

API CALL INVOCATION EXAMPLE

// Example: Calling MiMo-V2.5-Pro 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-pro",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

15 providers
Xiaomimimo-v2.5-pro
$0.43 / $0.87$0.00 cache
ClinePasscline-pass/mimo-v2.5-pro
$1.74 / $3.48$0.01 cache
NanoGPTxiaomi/mimo-v2.5-pro
$0.43 / $0.87$0.00 cache
OpenCode Gomimo-v2.5-pro
$0.43 / $0.87$0.00 cache
Novita AIxiaomimimo/mimo-v2.5-pro
$0.52 / $1.04$0.00 cache
Xiaomi Token Plan (Europe)mimo-v2.5-pro
$0.00 / $0.00$0.00 cache
LLM Gatewaynovita/mimo-v2.5-pro
$0.52 / $1.04$0.00 cache
AI/ML APIxiaomi/mimo-v2.5-pro
$0.60 / $1.20$0.00 cache
LLMTRmimo/mimo-v2.5-pro
$0.43 / $0.87
AIHubMixmimo-v2.5-pro
$0.48 / $0.96$0.00 cache
Vercel AI Gatewayxiaomi/mimo-v2.5-pro
$0.30 / $0.61$0.00 cache
Xiaomi Token Plan (China)mimo-v2.5-pro
$0.00 / $0.00$0.00 cache
Hugging FaceXiaomiMiMo/MiMo-V2.5-Pro
$1.00 / $3.00
Kilo Gatewayxiaomi/mimo-v2.5-pro
$0.43 / $0.87$0.00 cache
Standard Computexiaomi/mimo-v2.5-pro
$0.43 / $0.87$0.00 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.00 / 1M tokens, saving up to 99% on repetitive MCP tool definitions and system instructions.