MiMo-V2.5-Pro
mimo-v2.5-proMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.... Built by Xiaomi.
Prices updated
Input price
$0.43
per 1M tokens · Standard
Output price
$0.87
per 1M tokens · Standard
Input limit
1.1M
tokens
Output limit
131K
tokens
Input formats
Output formats
MiMo-V2.5-Pro price history
2 price records since 9/25/2026
MiMo-V2.5-Pro cost calculator
$13/month
Standard pricing
Overview
What is MiMo-V2.5-Pro?
MiMo-V2.5-Pro is a text & reasoning model from Xiaomi. MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.... Its 1.1M context window and $0.43 input price make it a candidate for quality-focused production applications.
Benchmarks
MiMo-V2.5-Pro benchmarks & speed
How MiMo-V2.5-Pro scores on standardized evaluations, and where it lands among every model we track.
26.0
Intelligence Index
44tok/s
Output speed
1270
DesignArena Elo
Reasoning
GPQA Diamond
86.6%
Graduate-level scientific reasoning · top 37%
HLE
35.7%
Humanity's Last Exam · top 29%
Coding
SciCode
50.6%
Python for scientific computing · top 49%
Latency & design
- Time to first token
- 2.14s
- DesignArena win rate
- 51.8%
- Design battles judged
- 26,808
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
MiMo-V2.5-Pro pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.43
Per 1M tokens
Cached input · Standard
$0.0036
Per 1M tokens
Capabilities
MiMo-V2.5-Pro Tools
Tools available when using MiMo-V2.5-Pro through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Strengths and limitations
Strengths
- Measured results (AA Intelligence 26 · DesignArena Elo 1270) position it for demanding production work.
- 1.1M context supports large documents, repositories and extended conversations.
- Supports text & reasoning workloads in one model.
Limitations
- Real-world cost still depends on prompt length, response length and provider-specific billing rules.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider