MiMo-V2.6-Flash
MiMo-V2.6-Flash 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 $0.14 per 1M input tokens and $0.28 per 1M output tokens. It accepts text, images, audio and video and produces text. Typical uses: summarising supplied material, answering questions about provided content and drafting text from supplied material.
Price checked ยท source: OpenRouter
What MiMo-V2.6-Flash is
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. It accepts text, images, video, and audio, and produces text. The model therefore has multimodal inputs with a text output. Its context window holds up to 1,048,576 tokens, and its maximum output is 131,072 tokens. These limits describe how much input context it can accommodate and the upper bound for generated text; actual use depends on the request and configuration.
Supported capabilities include reasoning, tools, structured outputs, and response formats. These features let applications request a structured text response or connect the model to tools in a supported workflow. The facts do not identify particular tools, output schemas, or detailed behavior for each input modality, so those details should not be assumed. The stated capabilities describe broad interaction options rather than guarantees about a result.
That profile suits tasks involving supplied text or media and a text response, such as summarising source material, answering questions about provided content, drafting text, and creating structured outputs. The million-token context limit may fit prompts containing substantial source material, while the large output limit allows longer generated responses. The listed reasoning support may also suit multi-step prompts. MiMo-V2.6-Flash is most relevant when the intended workflow needs one or more of its accepted input types, text generation, or the listed response controls; the facts do not specify specialised domains or performance claims.
Key features
- Accepts text, images, video, and audio; produces text
- Supports a context of up to 1,048,576 tokens
- Allows up to 131,072 output tokens
- Supports tools, structured outputs, and response formats
- Includes reasoning support
Typical uses
- Summarising supplied material
- Answering questions about provided content
- Drafting text from supplied material
- Generating structured text responses
- Reasoning over long prompts
MiMo-V2.6-Flash pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.14 |
| Output, per 1M tokens | $0.28 |
| Cached input read, per 1M tokens | $0.0028 |
No price change since it was added on 21 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0037 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0048 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.021 |
MiMo-V2.6-Flash specifications
| Model id | xiaomi/mimo-v2.6-flash |
|---|---|
| Version | mimo-v2.6-flash-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-Flash yet.
Compare MiMo-V2.6-Flash
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.