mimo-v2.6-pro-ultraspeed · Xiaomi
MiMo-V2.6-Pro-UltraSpeed combines the flagship performance of MiMo-V2.6-Pro and offers up to 20× output speed to serve highly real-time interactive and latency-sensitive production scenarios.
MiMo-V2.6-Pro-UltraSpeed combines the flagship performance of MiMo-V2.6-Pro and offers up to 20× output speed to serve highly real-time interactive and latency-sensitive production scenarios.
MiMo V2.6 Pro Ultraspeed has a 1,048,576 token context window.
On AIHubMix, MiMo V2.6 Pro Ultraspeed costs $4.8 per million input tokens and $9.6 per million output tokens. Cached input reads are billed at $0.0384 per million tokens.
MiMo V2.6 Pro Ultraspeed accepts text, image, video and audio input.
MiMo V2.6 Pro Ultraspeed is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to mimo-v2.6-pro-ultraspeed — no other code changes needed.
MiMo V2.6 Pro Ultraspeed is developed by Xiaomi. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
MiMo V2.6 Pro Ultraspeed was released on September 22, 2026 by Xiaomi.
mimo-v2.6-flash is Xiaomi's latest model series. A fully multimodal, highly intelligent…
MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning…
xiaomi-mimo-v2.6-pro-free is the open free version of xiaomi-mimo-v2.6-pro. To maintain…
xiaomi-mimo-v2.6-flash-free is the open free version of xiaomi-mimo-v2.6-flash. To…
Only supports OpenAI-compatible formats.
MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can…
Use MiMo V2.6 Pro Ultraspeed via the AIHubMix unified API — one interface for every major LLM.