Xiaomi

20 indexed models

20 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

  • Published price : $0.0036 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.44 / input_tokens_per_million · openRouter ↗
  • Published price : $0.87 / output_tokens_per_million · openRouter ↗

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

  • Published price : $0.0028 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.14 / input_tokens_per_million · openRouter ↗
  • Published price : $0.28 / output_tokens_per_million · openRouter ↗

Xiaomi: MiMo-V2.5-Pro

xiaomi/mimo-v2.5-pro-20260422

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously comple

Context window
1,024,000
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 26
  • OpenRouter Benchmarks: 85.728%

Inference prices

  • Published price : $0.10 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.48 / input_tokens_per_million · openRouter ↗
  • Published price : $1.80 / output_tokens_per_million · openRouter ↗

Xiaomi: MiMo-V2.5

xiaomi/mimo-v2.5-20260422

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, ext

Context window
1,000,000
Input modalities
text, audio, image, video
Output modalities
text
Capabilities
audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 21.8
  • OpenRouter Benchmarks: 82.417%

Inference prices

  • Published price : $0.08 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.40 / input_tokens_per_million · openRouter ↗
  • Published price : $2.00 / output_tokens_per_million · openRouter ↗

mimo-v2.5

cheaperInference/mimo-v2.5

Context window
1,000,000
Maximum output
65,536
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch

Inference prices

mimo-v2.5-pro

cheaperInference/mimo-v2.5-pro

Context window
1,050,000
Maximum output
131,072
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

mimo-v2.6-flash

cheaperInference/mimo-v2.6-flash

Context window
1,048,576
Maximum output
131,072
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

mimo-v2.6-pro

cheaperInference/mimo-v2.6-pro

Context window
1,048,576
Maximum output
131,072
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

mimo-v2.6-pro-ultraspeed

cheaperInference/mimo-v2.6-pro-ultraspeed

Context window
1,048,576
Maximum output
131,072
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

XiaomiMiMo/MiMo-7B-Base

vertexAI/publishers/hf-xiaomimimo/models/mimo-7b-base@001

Input modalities
text
Output modalities
text

XiaomiMiMo/MiMo-7B-RL

vertexAI/publishers/hf-xiaomimimo/models/mimo-7b-rl@001

Input modalities
text
Output modalities
text

XiaomiMiMo/MiMo-Embodied-7B

vertexAI/publishers/hf-xiaomimimo/models/mimo-embodied-7b@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

XiaomiMiMo/MiMo-VL-7B-RL

vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-rl@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Benchmarks

  • MMBench: 98.9%

XiaomiMiMo/MiMo-VL-7B-SFT

vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-sft@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

XiaomiMiMo/MiMo-VL-7B-SFT-2508

vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-sft-2508@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Xiaomi: mimo-v2.5-asr

xiaomiMiMo/mimo-v2.5-asr

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

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

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