baidu/ernie-4.5-vl-424b-a47b
123,000 context · $0.42/M input tokens · $1.25/M output tokens
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...
Pago por uso
Sin costos iniciales, paga solo por lo que uses
Usa los siguientes ejemplos de código para integrar con nuestra API:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="baidu/ernie-4.5-vl-424b-a47b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)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 p
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.
| Specification | Value |
|---|---|
| Provider | Baidu |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 123000 tokens |
| Max Output | 16000 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.5 |
| Output | $1.4 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: baidu/ernie-4.5-vl-424b-a47b
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="baidu/ernie-4.5-vl-424b-a47b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/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": "Hello!"}]
}'baidu/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...
Entrada
$0.42 /M
Salida
$1.25 /M
Contexto
123K
Salida máx.
16K
Visión
Compatible
Accede a Ernie 4.5 Vl 424b A47b mediante nuestra API unificada — compatible con OpenAI, sin arranques en frío, precios transparentes.
Precios en WaveSpeedAI: $0.42 por millón de tokens de entrada y $1.25 por millón de tokens de salida. El prompt caching y el procesamiento por lotes se facturan por separado y reducen el coste efectivo en cargas largas y repetitivas.
Ernie 4.5 Vl 424b A47b admite hasta 123K tokens de contexto y hasta 16K tokens de salida por solicitud.
Sí. WaveSpeedAI expone Ernie 4.5 Vl 424b A47b a través de un endpoint compatible con OpenAI en https://llm.wavespeed.ai/v1. Apunta el SDK oficial de OpenAI a esta base URL con tu clave API de WaveSpeedAI — sin más cambios de código.
Inicia sesión en WaveSpeedAI, crea una clave API en Access Keys y envía una solicitud a https://llm.wavespeed.ai/v1/chat/completions con el id de modelo mostrado arriba. Las cuentas nuevas reciben créditos gratuitos para evaluar Ernie 4.5 Vl 424b A47b antes de pagar por token.