Identity
- Status
- active
- Developer ID
mimo-v2.6-pro- Released
- Sep 21, 2026
- Version
- MiMo-V2.6-Pro
- License
- MIT
MiMo-V2.6-Pro is Xiaomi's open-weight, native omni-modal sparse mixture-of-experts model for reasoning and agentic workloads.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenrouterAvailable | $0.435 | $0.87 | $0.0036 | — | Sep 23, 2026 | Provider-reported |
Xiaomi MiMoAvailable | $0.435 | $0.87 | $0.0036 | — | Sep 22, 2026 | Provider-reported |
At a Glance
mimo-v2.6-proThis page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
MiMo V2.6 ProXiaomi | vs | GPT-6 AstraOpenAI | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | DeepSeek V4.1 FlashDeepSeek | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | Grok 4.6xAI | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | Qwen3.8 MaxQwen | cross-developer peersimage, text, video |
MiMo V2.6 ProXiaomi | vs | Kimi K3Moonshot AI | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | MiniMax M3MiniMax | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | GLM 5.3Z.ai | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | Hy4 previewTencent | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text, video |
MiMo V2.6 ProXiaomi | vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
MiMo V2.6 ProXiaomi | vs | cross-developer peersimage, text | |
MiMo V2.6 ProXiaomi | vs | Nova 2 LiteAmazon | cross-developer peersimage, text, video |
MiMo V2.6 ProXiaomi | vs | cross-developer peersimage, text | |
MiMo V2.6 ProXiaomi | vs | ERNIE 5.1Baidu | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | cross-developer peerstext | |
MiMo V2.6 ProXiaomi | vs | cross-developer peerstext | |
MiMo V2.6 ProXiaomi | vs | Phi-4 ReasoningMicrosoft | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | cross-developer peerstext | |
MiMo V2.6 ProXiaomi | vs | Sonar ProPerplexity | cross-developer peerstext |
MiMo V2.6 ProXiaomi | vs | Claude Mythos 5.1Anthropic | cross-developer peersimage, text |
Questions
MiMo-V2.6-Pro is Xiaomi's open-weight, native omni-modal sparse mixture-of-experts model for reasoning and agentic workloads. It is developed by Xiaomi and its current sourced lifecycle status is active.
MiMo V2.6 Pro's current record lists Text, Image, Video, and Audio as input and Text as output.
The current record lists a 1,049K-token context window and a maximum output of 131K tokens.
MiMo V2.6 Pro is marked as API-available. The directly sourced provider records currently include Openrouter and Xiaomi MiMo.
The current record lists 1T total parameters and 42B active parameters. Its architecture is Sparse mixture of experts.
MiMo V2.6 Pro's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are audio, image, text, and video.
The lowest directly sourced prices currently attached to MiMo V2.6 Pro are $0.435 per million input tokens through Openrouter and $0.87 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
MiMo V2.6 Pro is an open-weight model. Self-hosting is supported, and the recorded license is MIT.
No predecessor is recorded. No successor is recorded. Recorded aliases are mimo-v2.6-pro, MiMo-V2.6-Pro-RL, XiaomiMiMo/MiMo-V2.6-Pro-RL, and xiaomi/mimo-v2.6-pro-20260921.
The current compatible peer set includes GPT-6 Astra, Claude Fable 5.1, Gemini 3.1 Pro, DeepSeek V4.1 Flash, and Grok 4.6. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →