Author's Description
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....
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
MiMo-V2.5-Pro, Xiaomi’s flagship model, demonstrates exceptional reliability with a 100% success rate across all benchmarks, consistently providing usable responses. While it tends to have longer response times, ranking in the 17th percentile for speed, and is positioned at premium pricing levels (12th percentile), its performance in critical areas is robust. The model excels in General Knowledge and Ethics, achieving perfect 100% accuracy in both, and stands out as the most accurate model at its price point and speed in these categories. It also shows strong capabilities in Coding (96% accuracy, 96th percentile) and Reasoning (96% accuracy, 80th percentile). Instruction Following is a notable strength at 77% accuracy (82nd percentile). Hallucination rates are commendably low at 98% accuracy, indicating a strong ability to acknowledge uncertainty. Email Classification, while solid at 98% accuracy, is a more average performance compared to its other strengths. Overall, MiMo-V2.5-Pro is a highly reliable model with significant strengths in knowledge, ethical reasoning, and complex problem-solving, albeit at a premium cost and with longer processing times.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $1 |
| Completion | $3 |
| Input Cache Read | $0.2 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Xiaomi
|
Xiaomi | xiaomi/mimo-v2.5-pro-20260422 | 1M | $1 / 1M tokens | $3 / 1M tokens |
|
DeepInfra
|
DeepInfra | xiaomi/mimo-v2.5-pro-20260422 | 1M | $1 / 1M tokens | $3 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by xiaomi
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Xiaomi: MiMo-V2.5-Pro Unavailable | Apr 22, 2026 | — | 1M |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
| Xiaomi: MiMo-V2.5 Unavailable | Apr 22, 2026 | — | 1M |
Text input
Image input
Audio input
Video input
Text output
|
★★★ | ★★★★★ | $$$$$ |
| Xiaomi: MiMo-V2.5 | Apr 22, 2026 | — | 1M |
Text input
Image input
Audio input
Video input
Text output
|
★★ | ★★★★★ | $$$$$ |
| Xiaomi: MiMo-V2-Omni | Mar 18, 2026 | — | 262K |
Text input
Image input
Audio input
Video input
Text output
|
★★★ | ★★★★★ | $$$$$ |
| Xiaomi: MiMo-V2-Pro | Mar 18, 2026 | ~1T | 1M |
Text input
Text output
|
★ | ★★★★★ | $$$$$ |
| Xiaomi: MiMo-V2-Flash | Dec 14, 2025 | ~309B | 262K |
Text input
Text output
|
★★★★ | ★★★ | $$ |