Xiaomi MiMo
About Xiaomi MiMo
Flagship performance · Full modality · Built for professional workflows | Team Token Plan · Batch Inference (Batch API) now powered by V2.6 models.
With You, Every Step of the Way_
The all-in-one AI desktop app for professionals—high-quality office work, design, coding, and multimodal creation.
Offering a more cost-effective solution for your large-scale, non-real-time inference needs.
Website ↗Documentation ↗
Source ↗ · 2026-11-12T04:15:25.649231126ZService status
unknown
Current inference service status unverified
7 indexed models
7 matching models
xiaomi/mimo-v2.6-pro-20260921
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding workloads. The model features a 1M-token context window and native multimodal capabilities. Optimize
- Context window
- 1,050,000
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 29.9
- OpenRouter Benchmarks: 90.123%
Inference prices
- Cached input / 1M tokens : $0.0018 / cache_read_tokens_per_million · xiaomiMiMo ↗
- Input / 1M tokens : $0.22 / input_tokens_per_million · xiaomiMiMo ↗
- Output / 1M tokens : $0.44 / output_tokens_per_million · xiaomiMiMo ↗
xiaomi/mimo-v2.6-flash-20260921
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token c
- Context window
- 1,050,000
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 26.7
- OpenRouter Benchmarks: 77.667%
Inference prices
- Cached input / 1M tokens : $0.0014 / cache_read_tokens_per_million · xiaomiMiMo ↗
- Input / 1M tokens : $0.07 / input_tokens_per_million · xiaomiMiMo ↗
- Output / 1M tokens : $0.14 / output_tokens_per_million · xiaomiMiMo ↗
xiaomiMiMo/mimo-v2.5-asr
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput, streaming, transcription
Inference prices
xiaomiMiMo/mimo-v2.5-tts
Use built-in high-quality voices for speech synthesis
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput, streaming
xiaomiMiMo/mimo-v2.5-tts-voiceclone
Replicate any voice from audio samples
- Input modalities
- text, audio
- Output modalities
- speech
- Capabilities
- audioInput, multimodal, speechOutput, streaming
xiaomiMiMo/mimo-v2.5-tts-voicedesign
Customize voice through text description
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput, streaming
xiaomi/mimo-v2.6-pro-ultraspeed-20260921
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x the output speed. The model features a 1M-token context
- Context window
- 1,048,576
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Inference prices
- Cached input / 1M tokens : $0.04 / cache_read_tokens_per_million · xiaomiMiMo ↗
- Input / 1M tokens : $4.35 / input_tokens_per_million · xiaomiMiMo ↗
- Output / 1M tokens : $8.70 / output_tokens_per_million · xiaomiMiMo ↗