MiMo-V2.6-Pro-UltraSpeed
FrontierVisionToolsXiaomi · Released September 2026
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.
It is part of Xiaomi's open-weight MiMo line, where Pro carries the capability, UltraSpeed serves the same checkpoint faster, and Flash covers high-volume work.
Facts and pricing
- Provider
- Xiaomi
- Context window
- 1.0M tokens
- Input price
- 52.2 credits / 1M tokens ($4.35 raw)
- Output price
- 104 credits / 1M tokens ($8.70 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try MiMo-V2.6-Pro-UltraSpeed now
What MiMo-V2.6-Pro-UltraSpeed is best for
- Hard problems where answer quality matters more than cost: strategy, analysis, difficult writing
- Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a frontier model like MiMo-V2.6-Pro-UltraSpeed:
- Review this business plan and give me the three hardest questions an investor would ask
- Rewrite this announcement so it lands with both engineers and executives
- I am choosing between two job offers, help me think through the tradeoffs
- Draft a technical design doc for a rate limiter, including failure modes
Xiaomi family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| MiMo-V2.6-Pro-UltraSpeed | 1.0M | 52.2 | 104 | September 2026 |
| MiMo-V2.6-Flash | 1.0M | 1.7 | 3.4 | September 2026 |
| MiMo-V2.6-Pro | 1.0M | 5.2 | 10.4 | September 2026 |
| MiMo-V2.5-Pro | 262K | 5.8 | 21.6 | April 2026 |
| MiMo-V2.5 | 1M | 4.8 | 24.0 | April 2026 |
Model comparisons
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Opus 5.5 vs Claude Fable 5.2
- GPT-6 Astra vs Claude Fable 5.2
- Claude Opus 5.5 vs Claude Opus 5
Frequently asked questions
- What is MiMo-V2.6-Pro-UltraSpeed?
- MiMo-V2.6-Pro-UltraSpeed is an AI model by Xiaomi. MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.
- How much does MiMo-V2.6-Pro-UltraSpeed cost on Zeplik?
- Input tokens cost 52.2 credits per million and output tokens 104 credits per million (1 credit = $0.10; the raw provider rates are $4.35 and $8.70 per million). New accounts start with free credits.
- How long can a conversation with MiMo-V2.6-Pro-UltraSpeed be?
- MiMo-V2.6-Pro-UltraSpeed has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
- Does MiMo-V2.6-Pro-UltraSpeed support images and tools?
- MiMo-V2.6-Pro-UltraSpeed accepts image input and supports tool calling.
Related models
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.
MiMo-V2.5 is a native omnimodal model by Xiaomi.
Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE).
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation.
More you can do with MiMo-V2.6-Pro-UltraSpeed
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on MiMo-V2.6-Pro-UltraSpeed or any model you pick.
- 1582 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.