By xiaomi ยท Updated 2026-11-08 ยท Open weights ยท mitReads imageslong-context / RAGreads images / documentsaudiostep-by-step reasoningopen weights / self-hostable
Xiaomi: MiMo-V2.5 is best suited for long-context / RAG, reads images / documents, audio, step-by-step reasoning, open weights / self-hostable. Access it through one Appmo API key alongside 452 other models โ Appmo's optimizer can route to it automatically when it is the best value for a request. Weights: huggingface.co/XiaomiMiMo/MiMo-V2.5.
curl https://appmo.com/v1/chat/completions \
-H "Authorization: Bearer $APPMO_KEY" \
-d '{"model":"xiaomi/mimo-v2.5","messages":[{"role":"user","content":"Hello"}]}'How much does Xiaomi: MiMo-V2.5 cost?
Xiaomi: MiMo-V2.5 costs $0.4 per 1M input tokens and $2 per 1M output tokens ($0.8 blended), as of 2026-11-08. Prices are expected to fall as competition increases.
What is Xiaomi: MiMo-V2.5 best for?
Xiaomi: MiMo-V2.5 is best suited for long-context / RAG, reads images / documents, audio, step-by-step reasoning, open weights / self-hostable.
How do I use Xiaomi: MiMo-V2.5?
Send requests to Appmo's OpenAI-compatible endpoint with model id "xiaomi/mimo-v2.5" and one API key โ no separate provider account needed.
Is Xiaomi: MiMo-V2.5 open source?
Yes โ its weights are public on Hugging Face (XiaomiMiMo/MiMo-V2.5) under the mit license; check the license terms before commercial use.
Can Xiaomi: MiMo-V2.5 create images?
No. Xiaomi: MiMo-V2.5 can read and understand images, but it only writes text.