MiMo-V2.5
Native omni-modal perception model: text, images, video, and audio understood natively.
1M context window, purpose-built for multimodal agent scenarios.
Model Specs
Modality
Capabilities
Performance
Model Pricing
CNY
USD
Model Advantages
Native Omni-Modal Perception
Native understanding of images, video, audio, and text — precise cross-modal perception and long-horizon reasoning, with comprehensive perception capability at the industry frontier.
1M Context
Supports long-range tasks such as long video tracking, lengthy document analysis, and extended temporal reasoning, greatly expanding the model's applicability in complex, long-horizon scenarios.
Powerful Omni-Modal Agent Capability
Native agent execution across browsing, comprehension, reasoning, and operation — everyday task performance on par with mimo-v2.5-pro.
Performance Meets Efficiency
Maintains leading capability while achieving superior token efficiency, positioned at the Pareto frontier of performance and efficiency.
Choose Your Access Method
Pay-As-You-Go API
Top Up Balance
Prepaid model — pay only for tokens consumed. Balance visible in real time.
Sample Code
API format compatible with OpenAI and Anthropic protocols. Just change base_url and model to migrate.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("MIMO_API_KEY"),
base_url="https://api.xiaomimimo.com/v1"
)
completion = client.chat.completions.create(
model="mimo-v2.5",
messages=[
{
"role": "system",
"content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
},
{
"role": "user",
"content": "Please describe the content of the provided images, audio and videos respectively"
},
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
}
},
{
"type": "input_audio",
"input_audio": {
"data": "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
}
},
{
"type": "video_url",
"video_url": {
"url": "https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4"
},
"fps": 2,
"media_resolution": "default"
}
]
}
],
max_completion_tokens=1024,
stream=False,
extra_body={
"thinking": {"type": "disabled"}
}
)
print(completion.model_dump_json())Token Plan Subscription
Subscribe
Monthly or annual plans covering the full MiMo V2.5 model suite. Significantly more cost-effective than pay-as-you-go for high-volume scenarios.
Get Token Plan API Key
After subscribing, generate a dedicated API key from the Token Plan page. Same API format as pay-as-you-go.
Quick Integration
Just swap the key and base URL. Supports Claude Code, Cline, and other popular AI tools.
Use in MiMo Claw
MiMo Claw is powered by the latest MiMo-V2.5-Pro flagship model, MiMo-V2.5 for multimodal understanding, and MiMo-V2.5-TTS speech model. Try it free for a limited time.