ERNIE 4.5 VL 424B A47B

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.

ChatBaidu123k tokens$0.4578 / $1.3626 · 1M

baidu/ernie-4.5-vl-424b-a47b

Context
123k tokens
Completion cap
16,000
Tools
No
JSON
No
Released
2025-06-30

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "baidu/ernie-4.5-vl-424b-a47b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is ERNIE 4.5 VL 424B A47B?
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. ERNIE 4.5 VL 424B A47B runs on the Geek Hub API (OpenAI-compatible). Model id: baidu/ernie-4.5-vl-424b-a47b.
Is ERNIE 4.5 VL 424B A47B free?
No. Input is $0.4578 per 1M tokens and output is $1.3626 per 1M tokens on Geek Hub (markup included).
What is the context length of ERNIE 4.5 VL 424B A47B?
ERNIE 4.5 VL 424B A47B has a 123k tokens context window. It supports up to 16,000 completion tokens.
Does ERNIE 4.5 VL 424B A47B support tool calling and structured outputs?
ERNIE 4.5 VL 424B A47B does not advertise tool calling on this endpoint. Structured outputs are not listed for this endpoint.
When was ERNIE 4.5 VL 424B A47B released?
ERNIE 4.5 VL 424B A47B was released on 2025-06-30.