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 ↗ · 2026-11-12T04:15:25.649231126Z

Service status

unknown

Current inference service status unverified

7 indexed models

7 matching models

Xiaomi: MiMo-V2.6-Pro

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

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 ↗

Xiaomi: mimo-v2.5-asr

xiaomiMiMo/mimo-v2.5-asr

Input modalities
audio
Output modalities
transcription
Capabilities
audioInput, streaming, transcription

Inference prices

Xiaomi: mimo-v2.5-tts

xiaomiMiMo/mimo-v2.5-tts

Use built-in high-quality voices for speech synthesis

Input modalities
text
Output modalities
speech
Capabilities
speechOutput, streaming

Xiaomi: mimo-v2.5-tts-voiceclone

xiaomiMiMo/mimo-v2.5-tts-voiceclone

Replicate any voice from audio samples

Input modalities
text, audio
Output modalities
speech
Capabilities
audioInput, multimodal, speechOutput, streaming

Xiaomi: mimo-v2.5-tts-voicedesign

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

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 ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace