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

Contexto
123k tokens
Máx. completion
16,000
Tools
No
JSON
No
Lanzamiento
2025-06-30

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

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"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: baidu/ernie-4.5-vl-424b-a47b.
¿ERNIE 4.5 VL 424B A47B es gratis?
No. El input cuesta $0.4578 / 1M tokens y el output $1.3626 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de ERNIE 4.5 VL 424B A47B?
ERNIE 4.5 VL 424B A47B tiene una ventana de 123k tokens. Soporta hasta 16,000 tokens de completion.
¿ERNIE 4.5 VL 424B A47B soporta tool calling y structured outputs?
ERNIE 4.5 VL 424B A47B no publica tool calling en este endpoint. No lista structured outputs en este endpoint.
¿Cuándo se lanzó ERNIE 4.5 VL 424B A47B?
ERNIE 4.5 VL 424B A47B se lanzó el 30 de junio de 2025.