$0.14 / $0.28per 1M tokens in / out
$0.003cache read · −98%
$0.019per task at thinking?
#46on OpenRouter by tokens · 446.7B / week
Price sheetper 1M tokens
| Input | $0.14 | list |
| Output | $0.28 | |
| Cache read | $0.003 | −98% vs input |
| Context · max output | 1M · 131K | tokens |
Where to buy4 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.14 | $0.28 | — |
| Xiaomilab | $0.14 | $0.28 | 1M |
| Novita | $0.17 | $0.34 | — |
| Venice | $0.40 | $2 | 1M |
In Xiaomi's line-upper 1M in / out
| MiMo v2.5 | $0.14 / $0.28 | this model |
| MiMo v2.6 Flash | $0.14 / $0.28 | 0% |
| MiMo v2.6 Pro | $0.43 / $0.87 | 3.1× |
| MiMo v2.6 Pro UltraSpeed | $4.35 / $8.70 | 31.1× |
Cheaper for the same workvs MiMo v2.5
| Agnes 2.5 Pro Beta | -14% | score +61% | $0.10 / $0.30 |
| GPT-6 Luna medium | -8% | score +37% | $0.017 |
| GPT-5.6 Luna medium | -18% | score +15% | $0.016 |
| Ling 3.0 Flash VL thinkingOpen | -49% | score +13% | $0.06 / $0.18 |
| Ling 3.0 Flash Fin thinkingOpen | -49% | same score | $0.06 / $0.18 |
Pricing questions
How much does MiMo v2.5 cost?›
$0.14 per 1M input tokens and $0.28 per 1M output tokens. Cached input is $0.003. One Intelligence Index task costs about $0.019 at the default effort.
Is MiMo v2.5 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 $0.003 per 1M, 98% below the input price.
What is a cheaper alternative to MiMo v2.5?›
Agnes 2.5 Pro Beta costs -14% per task with a score +61% on Humanity's Last Exam.