# MiMo-V2.6 Pro UltraSpeed

> The speed edition of Xiaomi's MiMo-V2.6 Pro, listed September 2026: the same flagship capability at up to 20x the output speed.

- Maker: Xiaomi
- Line: MiMo
- Canonical page: https://ai-tldr.dev/models/mimo-v2-6-pro-ultraspeed/
- Updated: 2026-09-22

## In short

MiMo-V2.6 Pro UltraSpeed is the speed edition of Xiaomi's MiMo-V2.6 Pro, listed September 2026: the same flagship capability at up to 20x the output speed. It has a 1M-token context window and costs $4.35 per million input tokens and $8.70 per million output tokens. You can use it through Xiaomi MiMo Open Platform.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 1M (max output 128K) | [1] |
| Input price | $4.35 / 1M tokens (cached $0.036) | [2] |
| Output price | $8.70 / 1M tokens | [2] |
| Licence | Proprietary · API only | [1] |
| Released | 22 September 2026 | [3] |

## Sources

1. [MiMo-V2.6-Pro-RL model card (the flagship it is built on)](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL)
2. [MiMo-V2.6-Pro-UltraSpeed model page](https://mimo.mi.com/models/en-US/mimo-v2.6-pro-ultraspeed)
3. [MiMo model release notes](https://mimo.mi.com/docs/en-US/updates/model)

## Overview

MiMo-V2.6-Pro-UltraSpeed is the third model listed in Xiaomi's MiMo-V2.6 series, alongside MiMo-V2.6 Pro and MiMo-V2.6 Flash. Xiaomi's own model-updates page dates the series 2026-09-22 and describes this entry as "Flagship V2.6-Pro performance, up to 20x faster. Built for real-time and latency-sensitive workloads."

Where Pro and Flash are positioned by capability and cost, UltraSpeed is positioned purely by latency. Its model page states that it "retains V2.6-Pro's full flagship-level capability with zero compromise" while delivering "up to 20x faster output speed than V2.6-Pro". Xiaomi does not document the mechanism behind the speed-up on that page, and publishes no separate benchmark table for it.

The specification otherwise mirrors the flagship: a 1 million-token context window, up to 128K tokens of output, and omnimodal input — text, image, video and audio in, text out. Unlike MiMo-V2.6-Pro-RL and MiMo-V2.6-Flash-RL, which Xiaomi publishes as MIT-licensed checkpoints on Hugging Face, no UltraSpeed checkpoint appears under the XiaomiMiMo organisation: it is reached through the MiMo API platform rather than downloaded.

Pricing is listed per million tokens: $4.35 for input on a cache miss, $0.036 for input on a cache hit, and $8.70 for output (¥30, ¥0.25 and ¥60 respectively).

## Pricing

- Input: $4.35 / 1M tokens
- Cached input: $0.036 / 1M tokens
- Output: $8.70 / 1M tokens

Cache-miss input $4.35, cache-hit input $0.036, output $8.70 (¥30 / ¥0.25 / ¥60).

Source: https://mimo.mi.com/models/en-US/mimo-v2.6-pro-ultraspeed

## Strengths

- Up to 20x the output speed of MiMo-V2.6 Pro, at what Xiaomi describes as the same flagship-level capability
- The full 1M-token context and 128K-token output ceiling of the flagship, not a shortened variant
- Omnimodal input — text, image, video and audio — in a latency-tuned model
- A cache-hit input price of $0.036 per 1M tokens, roughly 1/120th of the cache-miss rate, for prompt-heavy repeat traffic

## Best for

- Reach for it when an interactive product — voice, live chat, a co-pilot — is bounded by how fast tokens arrive rather than by peak reasoning quality.
- Reach for it for latency-sensitive production paths where MiMo-V2.6 Pro is the right model but its output rate is the bottleneck.
- Reach for it when a long-context pipeline replays a large shared prefix, so most input tokens bill at the cache-hit rate.
- Reach for it for multimodal streams — screen, video or audio in, text out — that have to keep up with the user in real time.

## How to access

- [Xiaomi MiMo Open Platform](https://platform.xiaomimimo.com) — model id `mimo-v2.6-pro-ultraspeed`

## MiMo versions

- MiMo-V2.6 Pro UltraSpeed (22 September 2026): The latency-tuned member of the MiMo-V2.6 series: flagship capability at up to 20x the output speed, API-only. — this page
- [MiMo-V2.6 Pro](https://ai-tldr.dev/models/mimo-v2-6-pro/) (21 September 2026): Flagship checkpoint of the MiMo-V2.6 series: 1.02T/42B-active omnimodal MoE, 1M context, MIT.
- [MiMo-V2.6 Flash](https://ai-tldr.dev/models/mimo-v2-6-flash/) (21 September 2026): The efficiency-balanced sibling: 309B total, 15B activated, same modalities and context.

## FAQ

### How is MiMo-V2.6 Pro UltraSpeed different from MiMo-V2.6 Pro?

Speed. Xiaomi's model page says UltraSpeed "retains V2.6-Pro's full flagship-level capability with zero compromise" while delivering "up to 20x faster output speed". The context window (1M), output ceiling (128K) and input modalities are the same.

### Can I download MiMo-V2.6 Pro UltraSpeed weights?

No. Xiaomi publishes MiMo-V2.6-Pro-RL and MiMo-V2.6-Flash-RL as MIT-licensed checkpoints on Hugging Face, but no UltraSpeed checkpoint is listed under the XiaomiMiMo organisation. It is served through the MiMo API platform.

### What does MiMo-V2.6 Pro UltraSpeed cost?

Per million tokens: $4.35 input on a cache miss, $0.036 input on a cache hit, and $8.70 output — ¥30, ¥0.25 and ¥60 in CNY.

### What modalities does it accept?

Text, image, video and audio as input; text as output — the same omnimodal input set as MiMo-V2.6 Pro.

### How does Xiaomi achieve the speed-up?

Xiaomi does not say. The model page states the speed claim and the latency-sensitive positioning but documents no mechanism, and publishes no separate benchmark table for UltraSpeed.

## Links

- [MiMo-V2.6-Pro-UltraSpeed model page](https://mimo.mi.com/models/en-US/mimo-v2.6-pro-ultraspeed)
- [MiMo model release notes](https://mimo.mi.com/docs/en-US/updates/model)
- [Xiaomi MiMo API Platform](https://platform.xiaomimimo.com)
- [MiMo-V2.6-Pro-RL model card (the flagship it is built on)](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/mimo-v2-6-pro-ultraspeed/