MiMo-V2.5
Xiaomi · Open weights · Released Apr 22, 2026 · xiaomi/mimo-v2.5
1.05M contextVisionToolsReasoningStructured outputPrompt cachingAudio inputOpen weights
Available from 5 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| GMIGMICloud | $0.119 | $0.238 | $0.003 | 1.05M | fp8 | 3s | 51 tok/s | 88.5% |
| XIXiaomi1ST PARTY | $0.14 | $0.28 | $0.003 | 1.05M | fp8 | 21.1s | 52 tok/s | 99.5% |
 Parasail | $0.14 | $0.28 | $0.05 | 1.05M | fp8 | 0.61s | 130 tok/s | 99.5% |
 Novita | $0.168 | $0.336 | $0.003 | 1.05M | fp8 | 0.91s | 48 tok/s | 98.9% |
 DeepInfra | $0.40 | $2.00 | $0.08 | 262K | bf16 | 0.71s | 39 tok/s | 98.2% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.119 / $0.238
per MTok in / out
CACHE READ $0.003
About
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...
Specifications
Context window1,050,000
Max output131,072
Modalities intext, audio, image, video
Modalities outtext
LicenseOpen weights
ReleasedApr 22, 2026
TokenizerOther
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/xiaomi/mimo-v2.5)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks43 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.