MiMo-V2.6-Pro-UltraSpeed
MiMo-V2.6-Pro-UltraSpeed is a large language model made by Xiaomi, added to the catalog on 21 Sep 2026. It has a context window of 1,048,576 tokens and costs $4.35 per 1M input tokens and $8.70 per 1M output tokens. It accepts text, images, audio and video and produces text. Typical uses: summarising long documents, reviewing mixed-media records and analyzing detailed prompts.
Price checked · source: OpenRouter
What MiMo-V2.6-Pro-UltraSpeed is
Xiaomi MiMo-V2.6-Pro-UltraSpeed is a multimodal foundation model and the fast-speed edition of MiMo-V2.6-Pro. It accepts text, images, video, and audio as input, and produces text. Its context length is 1,048,576 tokens, and its maximum output is 131,072 tokens. The model also supports reasoning, tools, structured outputs, and response formats.
A context window of this size can suit requests that bring together extensive source material, long exchanges, or multiple kinds of input. The output allowance leaves room for lengthy text responses when a task calls for them. Its multimodal inputs are relevant to workflows involving text alongside images, video, or audio, while the text-only output provides a consistent format for generated responses. Tool support may fit workflows that connect model responses with tools, and structured-output and response-format support can be useful when responses need a defined organization.
Possible applications include reviewing long mixed-media records, summarizing supplied documents, and drafting organized written responses. The model’s listed reasoning support may also suit analytical prompts that require working with detailed context. Its combination of a large context window and multiple input modalities is relevant when a task involves gathering information from varied materials before producing a text response. The catalog identifies it as built from the same checkpoint as MiMo-V2.6-Pro, but does not specify further details about individual media-processing capabilities or performance on particular tasks.
Key features
- Accepts text, image, video, and audio input
- Produces text output
- Has a context length of 1,048,576 tokens
- Supports up to 131,072 output tokens
- Supports tools, reasoning, structured outputs, and response formats
Typical uses
- Summarising long documents
- Reviewing mixed-media records
- Analyzing detailed prompts
- Drafting structured text responses
MiMo-V2.6-Pro-UltraSpeed pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $4.35 |
| Output, per 1M tokens | $8.70 |
| Cached input read, per 1M tokens | $0.036 |
No price change since it was added on 21 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0048 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.116 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.148 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.666 |
MiMo-V2.6-Pro-UltraSpeed specifications
| Model id | xiaomi/mimo-v2.6-pro-ultraspeed |
|---|---|
| Version | mimo-v2.6-pro-ultraspeed-20260921 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 Sep 2026 |
| Input types | text, image, video, audio |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for MiMo-V2.6-Pro-UltraSpeed yet.
Compare MiMo-V2.6-Pro-UltraSpeed
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.