Mimo V2 Pro

LLM
Xiaomi

Mimo V2 Pro is a foundation model built for agentic workloads, designed to orchestrate complex workflows, drive production engineering tasks, and support coding and general agent frameworks across a 1M token context.

Context tokens

1,048,576

Output tokens

131,100

Training cutoff

May 1, 2025

Released

Mar 20, 2026

Schema

This is a reasoning model that uses thinking mode by default. Pricing scales up for prompts exceeding 256K tokens.

Schema documentation

Capabilities

Tool use
Structured output
Thinking

Supported tools

No tools enabled.

Pricing

TypeCreditsUnits
Input26.60Credits per 1k tokens
Output79.80Credits per 1k tokens
Cache hit5.32Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Mimo V2 Pro in the model experiments page. You can compare it with other models side by side.