MiMo-V2.5
xiaomi/mimo-v2.5
- context
- 1.05M
- modalities
- text, audio, image, video → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Long context, Low cost
Overview
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...
Providers
- DeepInfraView DeepInfra
- GMICloudView GMICloud
- NovitaView Novita
- StreamLakeView StreamLake
- VeniceView Venice
- XiaomiView Xiaomi
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| DeepInfra | $0.133 | $0.266 |
| GMICloud | $0.119 | $0.238 |
| Novita | $0.168 | $0.336 |
| StreamLake | $0.168 | $0.336 |
| Venice | $0.40 | $2.00 |
| Xiaomi | $0.14 | $0.28 |
DeepInfra
- input / 1M
- $0.133
- output / 1M
- $0.266
GMICloud
- input / 1M
- $0.119
- output / 1M
- $0.238
Novita
- input / 1M
- $0.168
- output / 1M
- $0.336
StreamLake
- input / 1M
- $0.168
- output / 1M
- $0.336
Venice
- input / 1M
- $0.40
- output / 1M
- $2.00
Xiaomi
- input / 1M
- $0.14
- output / 1M
- $0.28
Use this model
through Nautili
Route requests to MiMo-V2.5 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.