MODELS
Xiaomi: MiMo-V2.5
by Xiaomi
Overview
Native omni-modal agent foundation model from Xiaomi MiMo with a 1M-token context window for image, video, audio, and text understanding.
Details
MiMo-V2.5 is part of Xiaomi’s MiMo-V2.5 series. Xiaomi’s official MiMo homepage describes mimo-v2.5 as an omni-modal agent foundation model with a 1M context window and support for image, video, audio, and text understanding. Xiaomi’s MiMo API Open Platform states that the MiMo-V2.5 series, including mimo-v2.5 and mimo-v2.5-pro, was officially open-sourced under the MIT license. OpenRouter describes MiMo-V2.5 as a native omnimodal model by Xiaomi that delivers Pro-level agentic performance at roughly half the inference cost and surpasses MiMo-V2-Omni in multimodal perception across image and video understanding.
When to Use
Use for omni-modal agent workflows that need image video audio and text understanding in one model. Use when a 1M-token context window is useful for long-context multimodal tasks. Evaluate when comparing Xiaomi MiMo-V2.5 against MiMo-V2-Omni or other multimodal foundation models.
Getting Started
- Visit the official Xiaomi MiMo homepage to review the MiMo-V2.5 series and model positioning.
- Read the MiMo-V2.5 open-source announcement on the Xiaomi MiMo API Open Platform for availability and license details.
- Inspect the OpenRouter model page if you want to evaluate MiMo-V2.5 through OpenRouter-supported access.
- Run a small multimodal trial with representative image
- video
- audio
- and text inputs before production use.
Key Features
- •Native omni-modal model from Xiaomi MiMo
- •1M-token context window
- •Supports image
- •video
- •audio
- •and text understanding
- •MiMo-V2.5 series includes mimo-v2.5 and mimo-v2.5-pro
- •Open-sourced under the MIT license according to Xiaomi MiMo API Open Platform
Capabilities
- •multimodal-understanding
- •image-understanding
- •video-understanding
- •audio-understanding
- •text-understanding
- •long-context
- •agentic-workflows
Last updated May 31, 2026