Xiaomi
MiMo-V2.6-Flash
Xiaomi's MiMo-V2.6-Flash, released and open-sourced under an MIT license on September 22, 2026, is a full-modality reasoning model in the MiMo-V2.6 series. It natively understands text, image, video and audio and returns text, with a 1M-token context window and up to 128K output, plus deep thinking, tool calling and web search. Xiaomi positions it on the Pareto frontier — matching pro-tier models on real-world workflows at low cost and high token efficiency. Hosted API pricing is $0.14 input and $0.28 output per million tokens (cache hits $0.0028 input), OpenAI- and Anthropic-protocol compatible, with weights published on Hugging Face.
- Provider
- Xiaomi
- Context
- 1MCatalog · As of Oct 21, 2026Within 30d
- yno subscription tier
- Pro
- Released
- Sep 22, 2026
- Speed
- Medium
- Reasoning
- Expert
- Modality
- Multimodal
Benchmarks
Quality
- AA Intelligence Index
Speed and latency
- Output speed
- 37.67tokens/sConfiguration: Prompt length: 1,000 · Parallel queries: 1Artificial Analysis · Date unknownAge unknown
- Time to first token
- 2.92sConfiguration: Prompt length: 1,000 · Parallel queries: 1Artificial Analysis · Date unknownAge unknown
- Time to first answer token
- 56.02sConfiguration: Prompt length: 1,000 · Parallel queries: 1Artificial Analysis · Date unknownAge unknown
API pricing
- API input cost
- API output cost
Benchmark variant: MiMo-V2.6-Flash
AA data retrieved Nov 2, 2026 · Artificial Analysis
Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology
Capabilities
- Open Source
- Reasoning
- Vision
- Long Context
Use cases
- High-frequency API calls
- Large-scale multimodal tasks
- Self-hosted AI
- Agentic workflows
Strengths
- MIT-licensed open weights
- Full text/image/video/audio input
- 1M-token context
- Pareto-frontier cost efficiency
Best for
High-frequency, large-scale multimodal workloads needing open weights at low cost
No credit card required
Related models
Frequently asked
- What is MiMo-V2.6-Flash?
- Xiaomi's MiMo-V2.6-Flash, released and open-sourced under an MIT license on September 22, 2026, is a full-modality reasoning model in the MiMo-V2.6 series. It natively understands text, image, video and audio and returns text, with a 1M-token context window and up to 128K output, plus deep thinking, tool calling and web search. Xiaomi positions it on the Pareto frontier — matching pro-tier models on real-world workflows at low cost and high token efficiency. Hosted API pricing is $0.14 input and $0.28 output per million tokens (cache hits $0.0028 input), OpenAI- and Anthropic-protocol compatible, with weights published on Hugging Face.
- How much does MiMo-V2.6-Flash cost in yno.ai?
- MiMo-V2.6-Flash is available on the Pro tier of yno.ai.
- What can MiMo-V2.6-Flash do?
- MiMo-V2.6-Flash is best for High-frequency, large-scale multimodal workloads needing open weights at low cost. Its main capabilities include Open Source, Reasoning, Vision, Long Context.
- How does MiMo-V2.6-Flash compare to other models?
- MiMo-V2.6-Flash excels at MIT-licensed open weights and is recommended for High-frequency API calls, Large-scale multimodal tasks, Self-hosted AI, Agentic workflows. See related models below.
- How do I use MiMo-V2.6-Flash in yno.ai?
- Sign up for yno.ai, select MiMo-V2.6-Flash from the model picker, and start chatting.