MiMo-V2.5

MiMo-V2.5

Xiaomi

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...

What is MiMo-V2.5?

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...

Specifications

  • Developer: Xiaomi
  • Context window: 1.0M tokens
  • Max output: 131.1K tokens
  • Input modalities: text, audio, image, video
  • Output modalities: text
  • Input price: $0.4000 per 1M tokens
  • Output price: $2.00 per 1M tokens
  • Knowledge cutoff:
  • Supported parameters: frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, response_format, stop, temperature, tool_choice, tools, top_p

Use MiMo-V2.5 with PromptLayer

PromptLayer lets teams manage, evaluate, and observe prompts that run on MiMo-V2.5 alongside every other model in their stack. Version prompts, run evals across models, and ship safe rollouts from the same dashboard.

Ready to try it yourself? Sign up for PromptLayer and start managing your prompts in minutes.

Socials
PromptLayer
Company
All services online
Location IconPromptLayer is located in the heart of New York City
PromptLayer © 2026