Xiaomi Models
Beijing-based technology company building open MiMo language models. Retains API prompts but does not train on them. Requesty routes to 2 Xiaomi models starting at $0.14 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
mimo-v2.5-proIntelligence Index
42.2
Coding Index
60.2
GPQA Diamond
86.6%
Terminal-Bench Hard
43.2%
All Xiaomi models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
mimo-v2.5-pro | 1.0M | 131K | $0.43 | $0.87 | 🔧⚡ | 60 |
mimo-v2.5 | 1.0M | 131K | $0.14 | $0.28 | 👁🔧⚡ | N/A |
About Xiaomi on Requesty
How many Xiaomi models are available through Requesty?
Requesty routes to 2 Xiaomi models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Xiaomi model?
The cheapest Xiaomi model starts at $0.14 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Xiaomi pricing?
No. Requesty passes through exactly what Xiaomi charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Xiaomi models?
Xiaomi's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Xiaomi models hosted?
Xiaomi models are hosted in 🇨🇳 China. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Xiaomi rows in the models explorer.