Skip to content
Xiaomi

MiMo-V2.6-Pro

MiMo-V2.6-Pro 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 $0.435 per 1M input tokens and $0.87 per 1M output tokens. It accepts text, images, audio and video and produces text. Typical uses: summarising lengthy text, answering questions about supplied material and working with mixed media inputs.

Price checked ยท source: OpenRouter

What MiMo-V2.6-Pro is

Xiaomi MiMo-V2.6-Pro is a foundation model from Xiaomi. It accepts text, image, video, and audio inputs and produces text. This makes it a multimodal model for tasks where information arrives in different formats and the requested result is written output. The catalog lists tool use, structured outputs, response formats, and reasoning among its supported capabilities.

The model has a context window of 1,048,576 tokens and can produce up to 131,072 output tokens. Its context capacity can accommodate lengthy material in a single request, while the output limit allows for extended text responses. These limits are useful to consider when a task involves substantial input or requires a long response; they describe capacity, not guaranteed response quality.

This combination suits work involving long documents, media inputs, and responses that need a defined structure. Possible tasks include summarising lengthy text, answering questions about supplied material, drafting written outputs from mixed media, and producing structured text for downstream workflows. Tool support is available, though the catalog does not specify particular tools or actions. The facts also do not identify particular languages, subject areas, or specialized task performance, so selection can be based on whether its listed input types, output format, context capacity, and supported controls fit the task.

Key features

  • Accepts text, image, video, and audio inputs
  • Produces text
  • Has a context window of 1,048,576 tokens
  • Supports up to 131,072 output tokens
  • Supports tools, structured outputs, response formats, and reasoning

Typical uses

  • Summarising lengthy text
  • Answering questions about supplied material
  • Working with mixed media inputs
  • Producing structured text
  • Generating extended written responses

MiMo-V2.6-Pro pricing

US dollars, list price through OpenRouter.

Checked
MiMo-V2.6-Pro price list
ItemStandard
Input, per 1M tokens$0.435
Output, per 1M tokens$0.87
Cached input read, per 1M tokens$0.0036

No price change since it was added on 21 Sep 2026.

What typical tasks cost with MiMo-V2.6-Pro
What a task costsCost
Answer a short question500 in / 300 out$0.0005
Summarise a 50-page PDF25,000 in / 800 out$0.012
Review a 2,000-line source file30,000 in / 2,000 out$0.015
Read a 300-page contract set150,000 in / 1,500 out$0.067
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

MiMo-V2.6-Pro specifications

MiMo-V2.6-Pro limits and identity
Model idxiaomi/mimo-v2.6-pro
Versionmimo-v2.6-pro-20260921
Context window1,048,576 tokensAbout 786,432 English words
Max output131,072 tokens
Knowledge cutoffNot published
Added to catalog21 Sep 2026
MiMo-V2.6-Pro capabilities
Input typestext, image, video, audio
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot 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 yet.

Compare MiMo-V2.6-Pro

Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.

MiMo-V2.6-Pro questions

How much does MiMo-V2.6-Pro cost?

MiMo-V2.6-Pro costs $0.435 per 1M input tokens and $0.87 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.012.

What is the context window of MiMo-V2.6-Pro?

1,048,576 tokens, or roughly 786,432 English words. It can write up to 131,072 tokens in one response.

Can MiMo-V2.6-Pro read images and PDFs?

It accepts text, images, audio and video as input. It produces text, so it cannot generate images.

How do I try MiMo-V2.6-Pro?

Use the "Try MiMo-V2.6-Pro" button on this page. It opens the chat with MiMo-V2.6-Pro selected; you type the question and press send.

Try MiMo-V2.6-Pro on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.