---
id: "xiaomi/mimo-v2.5-pro"
also: ["xiaomi/mimo-v2.5-pro-20260422", "XiaomiMiMo/MiMo-V2.5-Pro", "hf/XiaomiMiMo/MiMo-V2.5-Pro", "requesty/xiaomi/mimo-v2.5-pro", "vercel/xiaomi/mimo-v2.5-pro"]
card_usd_per_m: "0.435 in, 0.87 out, at xiaomi/fp8"
cheapest_list_usd_per_m: "0.3045 in, 0.609 out, at gmicloud/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.0612 in, 0.8694 out, at xiaomi/fp8 on openrouter"
context: 1024000
max_output: 235929
input: ["text"]
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: 15
gateways: "openrouter (7), requesty (3), vercel (3), hf (2)"
no_training: 11
trains: 2
retains_prompts: 8
coding: 60.2000
agentic: 21.3000
---
# Xiaomi: MiMo-V2.5-Pro

MiMo V2.5 Pro delivers significant improvements over its predecessor, MiMo-V2-Pro, in general agentic capabilities, complex software engineering, and long-horizon tasks. MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with a 1M-token context window.