Description
MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step...
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Xiaomi: MiMo-V2-Omni (xiaomi/mimo-v2-omni)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "xiaomi/mimo-v2-omni",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Xiaomi: MiMo-V2-Omni model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
- Images
- Audio
- Video
API Pricing
- Input: 0.4$ / 1M tokens
- Output: 2$ / 1M tokens
Token Limits
- Max Output: 65,536 tokens
- Max Context: 262,144 tokens
Subscription Tiers
- free
- pro
- ultimate