---
id: "xiaomi/mimo-v2.5"
also: ["xiaomi/mimo-v2.5-20260422", "XiaomiMiMo/MiMo-V2.5", "hf/XiaomiMiMo/MiMo-V2.5", "requesty/xiaomi/mimo-v2.5", "vercel/xiaomi/mimo-v2.5"]
card_usd_per_m: "0.14 in, 0.28 out, at xiaomi/fp8"
cheapest_list_usd_per_m: "0.119 in, 0.238 out, at gmicloud/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.006 in, 0.28 out, at xiaomi on requesty"
context: 1000000
max_output: 65536
input: ["text", "audio", "image", "video"]
output: ["text"]
released: "2026-04-22"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 16
gateways: "openrouter (8), hf (3), vercel (3), requesty (2)"
no_training: 10
trains: 2
retains_prompts: 6
coding: 56.8000
agentic: 15.8000
---
# Xiaomi: MiMo-V2.5

MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture. Built upon the MiMo-V2-Flash backbone and extended with dedicated vision and audio encoders, it delivers robust performance across multimodal perception, long-context reasoning, and agentic workflows.