MiMo-V2.6-Pro-UltraSpeed
Xiaomi· released 21 Sept 2026
xiaomi/mimo-v2.6-pro-ultraspeed- Input / 1M tokens
- $4.35
- Output / 1M tokens
- $8.7
Longest answer: 131K tokens
About
MiMo-V2.6-Pro-UltraSpeed is Xiaomi’s fast-speed edition of its MiMo-V2.6-Pro flagship foundation model. It is built from the same 1T MiMo-V2.6-Pro checkpoint and is described as matching the original model in quality while delivering roughly 10x speed. It supports reasoning and tools, and accepts text, image, video, and audio inputs while producing text. Its context window is 1,048,576 tokens, with a maximum output of 131,072 tokens. The listed release date is September 21, 2026. Pricing is $4.35 USD per 1M input tokens and $8.7 USD per 1M output tokens. The multimodal inputs and large context window may suit workflows that need to process varied media alongside text, while the speed positioning distinguishes this edition in Xiaomi’s model family.
Who it is for
It suits teams that need a Xiaomi model for text, image, video, and audio inputs, with reasoning and tool support. Its stated speed focus may be relevant for workloads prioritizing fast responses.
What is good
- Accepts text, image, video, and audio.
- Supports reasoning and tools.
- 1,048,576-token context window.
- Maximum output of 131,072 tokens.
What to know first
- Input costs $4.35 USD per 1M tokens.
- Output costs $8.7 USD per 1M tokens.
Verdict
MiMo-V2.6-Pro-UltraSpeed pairs broad input modalities and a very large context with Xiaomi’s stated speed focus. Its listed per-token prices are notably part of the decision for teams assessing fit.
Details
- Lab
- Xiaomiopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $4.35 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $8.7 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 131,072 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, video, audioopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Xiaomi Models: Pricing per 1M Tokens and Context (2026)5 listed
Sources
- openrouter.ai/xiaomi/mimo-v2.6-pro-ultraspeed· checked 3 Oct 2026