novita

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

Context

32K

Input

text, image

Output

text

Tool calling

Supported

About this model

ERNIE 4.5 VL is Baidu's 424-billion parameter vision-language Mixture of Experts model with 47B active parameters per token. It features advanced multimodal understanding, reasoning across text and images, and state-of-the-art performance in complex visual-language tasks.

Capabilities

text

Available through the unified API

image

Available through the unified API

Quick start

View API docs
curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "d3fbd59dcd7a4d8e973eb75dd3ce6eec",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

novita

d3fbd59dcd7a4d8e973eb75dd3ce6eec

Available

Input

$0.420 / 1M

Output

$1.250 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.420 / 1M
Output tokens$1.250 / 1M

Performance

Published evaluation results associated with this model.

Vision-Language Understanding

MMBench85.7
SEED-Bench82.3
MMMU68.9
VQAv282.1
GQA79.8

Multimodal Reasoning

ScienceQA-IMG87.5
MMMU-Reasoning65.4
ChartQA76.9
DocVQA73.2

Chinese VL Tasks

CMMMU71.8
CMMBench83.5
ZeroSCROLLS-CN78.6

Text Understanding

MMLU81.3
C-Eval79.7
GSM8K88.4
HumanEval62.8

Multimodal Safety

RedTeaming-VL91.2
SafetyBench-Multi87.9

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "d3fbd59dcd7a4d8e973eb75dd3ce6eec",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'