MiMo V2.6 Flash

Xiaomi
mimo-v2.6-flash
Released Sep 21, 2026
Providers
2
Context
1.0M
Input
$0.14/M
Output
$0.28/M

Xiaomi's MiMo-V2.6-Flash is the efficiency-balanced model of the MiMo-V2.6 series: a sparse Mixture-of-Experts model with 309B total and 15B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Built for agentic workloads such as long-horizon coding, tool use and computer use.

deepinfra/mimo-v2.6-flashQuantfp8
Input
$0.14/M
Output
$0.28/M
Context
1.0M
Max out
131K
Cache read
$0.00/M
Cache write
$0.14/M
Thinking out
$0.28/M
novita/mimo-v2.6-flashQuantUnspecified
Input
$0.14/M
Output
$0.28/M
Context
1.0M
Max out
131K
Cache read
$0.00/M
Cache write
$0.14/M
Thinking out
$0.28/M