---
id: "xiaomi/mimo-v2.6-pro-ultraspeed"
also: ["xiaomi/mimo-v2.6-pro-ultraspeed-20260921", "requesty/xiaomi/mimo-v2.6-pro-ultraspeed", "vercel/xiaomi/mimo-v2.6-pro-ultraspeed"]
card_usd_per_m: "4.35 in, 8.7 out, at xiaomi/fp8"
cheapest_list_usd_per_m: "4.35 in, 8.7 out, at xiaomi/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.2545 in, 8.7 out, at xiaomi on requesty"
context: 1048576
max_output: 131072
input: ["text", "image", "video", "audio"]
output: ["text"]
released: "2026-09-21"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 3
gateways: "openrouter (1), requesty (1), vercel (1)"
no_training: 2
trains: 1
retains_prompts: 3
---
# Xiaomi: MiMo-V2.6-Pro-UltraSpeed

MiMo V2.6 Pro UltraSpeed is Xiaomi's accelerated inference offering for MiMo V2.6 Pro, designed for interactive agents and workflows where response latency matters. It combines multimodal understanding of text, images, audio, and video with a 1M-token context window and up to 128K tokens of output. It supports deep thinking, tool calling, JSON mode, and prompt caching.