Xiaomi › MiMo v2.5 Pro › Pricing
$0.43 / $0.87per 1M tokens in / out
$0.004cache read · −99%
$0.054per task at thinking?
#78on OpenRouter by tokens · 143.3B / week
Price sheetper 1M tokens
| Input | $0.43 | list |
| Output | $0.87 | |
| Cache read | $0.004 | −99% vs input |
| Context · max output | 1M · 131K | tokens |
Where to buy4 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| AtlasCloud | $0.43 | $0.87 | 1M |
| Xiaomilab | $0.43 | $0.87 | 1M |
| Novita | $0.52 | $1.04 | — |
| DeepInfra | $1 | $3 | — |
In Xiaomi's line-upper 1M in / out
| MiMo v2.6 Flash | $0.14 / $0.28 | −68% |
| MiMo v2.5 Pro | $0.43 / $0.87 | this model |
| MiMo v2.6 Pro | $0.43 / $0.87 | 0% |
| MiMo v2.6 Pro UltraSpeed | $4.35 / $8.70 | 10× |
Cheaper for the same workvs MiMo v2.5 Pro
| Agnes 2.5 Pro Beta | -72% | score +36% | $0.10 / $0.30 |
| GPT-6 Luna xhigh | -22% | score +33% | $0.042 |
| Claude Haiku 5.5 medium | -13% | score +33% | $0.047 |
| GPT-5.6 Luna high | -19% | score +24% | $0.044 |
| Ling 3.0 Flash VL thinkingOpen | -83% | score -5% | $0.06 / $0.18 |
Pricing questions
How much does MiMo v2.5 Pro cost?›
$0.43 per 1M input tokens and $0.87 per 1M output tokens. Cached input is $0.004. One Intelligence Index task costs about $0.054 at the default effort.
Is MiMo v2.5 Pro free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.004 per 1M, 99% below the input price.
Is MiMo v2.5 Pro cheaper than MiMo v2 Pro?›
It costs the same per token: $0.43 / $0.87.
What is a cheaper alternative to MiMo v2.5 Pro?›
Agnes 2.5 Pro Beta costs -72% per task with a score +36% on Humanity's Last Exam.