MiMo-V2.5-Pro · deepinfra

MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in [MiMo-V2-Flash](https://github.com/XiaomiMiMo/MiMo-V2-Flash).

Base modelAll models on this baseAll models of the providerto the provider

Read also: Xiaomi MiMo API pricing: MiMo V2.6 Pro and V2.6 Flash at every provider

All Xiaomi MiMo models at every provider

Input, $/1M $1.00

Output, $/1M $3.00

Context 1 048 576

Max output 16 384

Accepts audio, text

Last checked 04.11.2026 12:00:14 UTC

Source —