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-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-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-v2.5-20260422
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 ↗
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
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
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
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
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
vertexAI/publishers/hf-xiaomimimo/models/mimo-7b-base@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-xiaomimimo/models/mimo-7b-rl@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-xiaomimimo/models/mimo-embodied-7b@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-rl@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
Benchmarks
vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-sft@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
vertexAI/publishers/hf-xiaomimimo/models/mimo-vl-7b-sft-2508@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
xiaomiMiMo/mimo-v2.5-asr
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput, streaming, transcription
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