← All models
X
Get an API keyxiaomi
xiaomi/…
1 serving nowup to 1024K context
Every xiaomi model we serve, with the numbers most providers leave out — the quantisation each endpoint actually runs at, measured first-token latency, and real uptime. Model ids are copyable: pass one straight to any OpenAI-compatible client.
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
- Parameters
- —
- Max context
- 1024K
| Quantisation | Context | p50 TTFT | Throughput | Uptime | Input /M | Output /M | Cached in /M | Status |
|---|---|---|---|---|---|---|---|---|
| FP8 | 1024K | — | — | 99.96% | $0.168 | $0.336 | $0.003 | live |
omnimodallong-contextagentreasoningvisionaudio
Qwen
DeepSeek
Ornith
Infersia
Google
Meta
OpenAI
Thinking Machines Lab
xAI