MiMo V2.5

Xiaomi's full-modal perception model supporting native understanding of images, videos, audio, and text with 1M context. Agent performance comparable to MiMo V2.5 Pro.

deepinfra/mimo-v2.5
STABLEScheduled for DeactivationGet Started
Streaming
Vision
Tools
Reasoning
JSON Output
Structured JSON
No ratings yetSign in to rate

DeepInfra Pricing for MiMo V2.5

View detailed pricing and capabilities for this provider.

Context: 262.1kQuant: bf16
Deactivating on Sep 29, 2026
Input
$0.4
/M tokens
Cache Read
$0.08
/M tokens
Output
$2
/M tokens
Get Started