MiMo-V2.6-Flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi using a Mixture-of-Experts architecture. It is designed to process text, images, video, and audio inputs while supporting complex reasoning and tool-calling capabilities.
MiMo-V2.6-Flash specs and pricing
- Provider: Xiaomi
- Released: September 21, 2026
- Context window: 1.1M tokens
- Max output: 131K tokens
- Input: text, images, video, audio
- Output: text
- Price: $0.14 input / $0.28 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What MiMo-V2.6-Flash is good at
- Analyzing long-form video and audio content
- Complex reasoning tasks requiring tool integration
- Multimodal data processing across text and images
To-dos to try with MiMo-V2.6-Flash
- Analyze this hour-long video recording and summarize the key discussion points.
- Read these five technical documents and extract the specific data points into a table.
- Use the provided tool to search for current market data and draft a summary report.
FAQ
- What types of media can MiMo-V2.6-Flash process? The model is capable of ingesting text, images, video, and audio files.
- Who developed this model? MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
- How much does MiMo-V2.6-Flash cost? MiMo-V2.6-Flash costs $0.14 per million input tokens and $0.28 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.43 credits ($1 = 100 credits).
- What is the context window of MiMo-V2.6-Flash? MiMo-V2.6-Flash can read up to 1.1M tokens at once and write up to 131K tokens in one reply.
- Can I use MiMo-V2.6-Flash without coding? Yes. In todo.is you pick MiMo-V2.6-Flash as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.