Models

MiMo-V2.5-Pro

MiMo-V2.5-Pro is a high-performance, cost-efficient language model from Xiaomi's MiMo series, optimized for fast inference and deployment on edge and mobile devices. It balances strong reasoning capabilities with low latency, making it suitable for on-device AI applications.

FastCheapReasoning
Input / 1M tokens
$0.435
Output / 1M tokens
$0.87
Output tokens/s
46.95
First-token seconds
2.01s
Supported plans
7

Benchmark history

Evaluations

11

Tau Banking

Measured Jul 10, 2026Source

Score

0.09

TAU2

Measured Jul 10, 2026Source

Score

0.94

Terminalbench V2 1

Measured Jul 10, 2026Source

Score

0.65

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.43

Lcr

Measured Jul 10, 2026Source

Score

0.73

Ifbench

Measured Jul 10, 2026Source

Score

0.8

Scicode

Measured Jul 10, 2026Source

Score

0.5

Hle

Measured Jul 10, 2026Source

Score

0.34

Gpqa

Measured Jul 10, 2026Source

Score

0.87

Artificial Analysis Coding Index

Measured Jul 10, 2026Source

Score

60.2

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

42.2

Plan availability

Products and plans that support this model

3
OpenCode Go

OpenCode Go

OpenCode Go is a low-cost monthly subscription that provides reliable access to a curated set of powerful open-source coding models, such as GLM-5.1, Kimi K2.6, and DeepSeek V4 Pro, for use with AI coding agents like OpenCode. Priced at $10/month with a $5 first month, it offers generous request limits to support developers.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server