MiMo-V2.6-Pro-UltraSpeed delivers MiMo V2.6 Pro flagship performance at up to 20x output speed.
It is described as built for real-time interaction and latency-sensitive production scenarios.
| Developer | Xiaomi |
|---|---|
| Model ID | xiaomi/mimo-v2.6-pro-ultraspeed |
| Release Date | September 21, 2026 |
| Context Window | 1,048,576 tokens (~1.0M) |
| Max Output Tokens | 131,072 tokens |
| Modalities | Image, Text, Video → Text |
| Capabilities | reasoning, streaming, structured (JSON schema) output, tool/function calling, vision |
Ultra-fast serving mode
The model is presented as an ultra-fast mode for MiMo-V2.6-Pro, with up to 20x faster output speed.
Real-time focus
Xiaomi describes it as suitable for workflows where response time matters.
Flagship performance
The model is characterized as providing V2.6-Pro's flagship performance.
Modality support
The model page lists Text, Image, Video, and Audio as input modalities, with Text output.
Platform features
The model page lists Omni-Modal Understanding, Deep Thinking, Tool Call, Streaming, Web Search, Structured Output, and Context Caching.
Live interaction
Suitable for interactive scenarios that need fast responses.
Latency-sensitive production
Suitable for production workflows where response time is critical.
Real-time workflows
Positioned for tasks that benefit from high generation speed.
Sources: https://mimo.xiaomi.com/mimo-v2-6 · https://mimo.mi.com/ · https://mimo.mi.com/docs/news/latest/v2-6
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "xiaomi/mimo-v2.6-pro-ultraspeed", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "xiaomi/mimo-v2.6-pro-ultraspeed", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"xiaomi/mimo-v2.6-pro-ultraspeed","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Cached input is billed at roughly a hundredth of the fresh-input rate, and Xiaomi lists cache writes as free for a limited time.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
MiMo V2.6 Pro UltraSpeed This page | Agentic workflows and structured output | |||
| Reasoning + agents | ||||
| Reasoning + agents |
It is built for real-time interaction and latency-sensitive production scenarios. It is described as a flagship V2.6-Pro performance mode for users who need extreme generation speed.
It delivers up to 20x output speed. The model is presented as a high-speed mode of V2.6-Pro.
It supports text, image, video, and audio inputs. The output modality is text.
Yes. The model is associated with deep thinking and reasoning-oriented use.
Yes. Streaming is listed among its capabilities.
Yes. Structured output is listed as a supported capability.
Yes. Tool call and web search are both listed as supported capabilities.
Yes. Vision is supported through its multimodal input capabilities.
Use the all-lowercase model name mimo-v2.6-pro-ultraspeed. The model is available as an API option on AI/ML API.
Yes. It is explicitly positioned for real-time interaction and workloads where response time matters.
