Description
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Baidu: ERNIE 4.5 VL 424B A47B (baidu/ernie-4.5-vl-424b-a47b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "baidu/ernie-4.5-vl-424b-a47b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Baidu: ERNIE 4.5 VL 424B A47B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
- Images
API Pricing
- Input: 0.42$ / 1M tokens
- Output: 1.25$ / 1M tokens
Token Limits
- Max Output: 16,000 tokens
- Max Context: 123,000 tokens
Subscription Tiers
- free
- pro
- ultimate