Moduck

Baidu: ERNIE 4.5 VL 424B A47B

Multimodal reasoning model for visual analysis, planning, and tool use

Model lab
Baidu
Model family
ernie
Modalitiesimage, text → text
Context window123,000
Maximum output16,000
InputUSD 0.336 / 1M tokens
OutputUSD 1 / 1M tokens
Try nowView docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/baidu/ernie-4-5-vl-424b-a47b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/baidu/ernie-4-5-vl-424b-a47b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

ERNIE 4.5 VL 424B A47B API Pricing

TypePrice information
InputUSD 0.336 / 1M tokens
OutputUSD 1 / 1M tokens

Performance

Performance trends

Throughput91.9 tok/sCurrent
Time to first token1.4 sCurrent
End-to-end latency7.4 sCurrent
Throughput
Current91.9 tok/s
Window average89.6 tok/s
Time to first token
Current1.4 s
Window average1.4 s
End-to-end latency
Current7.4 s
Window average7.5 s
Tail latency (P99)
Current15.1 s
Window average16.9 s
Prompt cache hit rate
Current18.2%
Window average24.5%
Error rate
Current0.0%
Window average0.2%

Availability

Uptime100%At least one provider responded
Availability100%Requests actually served
Error rate0%Share of failed requests
Served requests, hour by hour
24 hours agoNow

ERNIE 4.5 VL 424B A47B Compare models

ModelInput priceOutput priceContext windowCapabilities
ERNIE 4.5 VL 424B A47B This pageUSD 0.336 / 1M tokensUSD 1 / 1M tokens123,000Text output · Reasoning
ERNIE 4.5 21B A3BUSD 0.056 / 1M tokens · Context ≤ 120000 tokens · Maximum output 8000 tokensUSD 0.224 / 1M tokens · Context ≤ 120000 tokens · Maximum output 8000 tokens131,072Text output · Tool calling
DeepSeek V4.1 Flash 1017USD 0.028 / 1M tokens · Quantization fp4USD 0.4 / 1M tokens · Quantization fp41,000,000Text output · Reasoning · Tool calling
Mistral Large 4USD 0.544 / 1M tokensUSD 1.672 / 1M tokens1,048,576Text output · Reasoning · Tool calling
LongCat-2.5-PreviewUSD 0.6 / 1M tokensUSD 2.36 / 1M tokens1,000,000Text output · Reasoning · Tool calling

Model specifications

Input
image, text
Output
text
Context window
123,000
Maximum output
16,000
Release date
2025-06-30
Attachments
Yes
Reasoning
Yes
Tool calling
No
Structured output
No
Temperature setting
Yes
Open weights
Yes

Frequently asked questions

What is ERNIE 4.5 VL 424B A47B for?

Multimodal reasoning model for visual analysis, planning, and tool use

What inputs and outputs does ERNIE 4.5 VL 424B A47B support?

Recorded inputs: images, text; outputs: text.

How is ERNIE 4.5 VL 424B A47B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.336 / 1M tokens; Output USD 1 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for ERNIE 4.5 VL 424B A47B ?

Current model records list Context window 123,000 tokens; Maximum output 16,000 tokens.

What model parameter does the Quickstart use?

The example uses moduck/baidu/ernie-4-5-vl-424b-a47b. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.