ModelBench
Xiaomi logo
Models/Xiaomi

MiMo-V2-Pro

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

Source-linked mimo Closed weights Released 2026-03-18
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.435/1M tokens
Output price$0.87/1M tokens
Context window1.04858M
Max output131.072K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
× Attachments No
× Vision input No
× Open weights No
Creator
Xiaomi
Model family
mimo
Knowledge cutoff
2024-12
License
Not documented
Release date
2026-03-18
Model ID
xiaomi/mimo-v2-pro
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering MiMo-V2-Pro
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Xiaomi Token Plan (Europe) mimo-v2-pro 1.04858M Not listed Not listed - ReasoningTools Docs
Xiaomi Token Plan (China) mimo-v2-pro 1.04858M Not listed Not listed - ReasoningTools Docs
Xiaomi Token Plan (Singapore) mimo-v2-pro 1.04858M Not listed Not listed - ReasoningTools Docs
Xiaomi mimo-v2-pro 1.04858M $0.435 $0.87 $0.004 ReasoningTools Docs
Vercel AI Gateway xiaomi/mimo-v2-pro 1M $1 $3 $0.2 ReasoningTools Docs
ZenMux xiaomi/mimo-v2-pro 1M $1 $3 $0.2 ReasoningTools Docs
Abacus mimo-v2-pro 1.04858M $1 $3 $0.2 ReasoningTools Docs
Kilo Gateway xiaomi/mimo-v2-pro 1.04858M $1 $3 $0.2 ReasoningTools Docs
NanoGPT xiaomi/mimo-v2-pro 1.04858M $1 $3 $0.2 ReasoningToolsJSON Docs
NovitaAI xiaomimimo/mimo-v2-pro 1.04858M $2 $6 $0.4 ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
No comparable benchmark results

ModelBench does not infer quality from price, context size, or model name.

Read the methodology
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/xiaomi/mimo-v2-pro
curl
curl "https://www.modelbench.lol/api/v1/models/xiaomi/mimo-v2-pro"