Paddlepaddle: PaddleOCR VL

Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts

Model lab: Paddlepaddle
Model family: —

Model resources

Hugging Face

Modalitiestext, image → text

Context window131,072

Maximum output16,384

Input · Context ≤ 16384 tokens · Maximum output 16384 tokensUSD 0.016 / 1M tokens

Output · Context ≤ 16384 tokens · Maximum output 16384 tokensUSD 0.016 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to paddlepaddle/paddleocr-vl.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "paddlepaddle/paddleocr-vl"

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.

PaddleOCR VL API Pricing

Type	Price information
Input · Context ≤ 16384 tokens · Maximum output 16384 tokens	USD 0.016 / 1M tokens
Output · Context ≤ 16384 tokens · Maximum output 16384 tokens	USD 0.016 / 1M tokens

Performance

Performance trends

Throughput87.3 tok/sCurrent

Time to first token3.3 sCurrent

End-to-end latency7.5 sCurrent

Throughput

Current87.3 tok/s

Window average89.0 tok/s

Time to first token

Current3.3 s

Window average1.5 s

End-to-end latency

Current7.5 s

Window average7.5 s

Tail latency (P99)

Current30.2 s

Window average17.4 s

Prompt cache hit rate

Current31.0%

Window average22.7%

Error rate

Current2.1%

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

PaddleOCR VL Compare models

Model	Input price	Output price	Context window	Capabilities
PaddleOCR VLThis page	USD 0.016 / 1M tokens · Context ≤ 16384 tokens · Maximum output 16384 tokens	USD 0.016 / 1M tokens · Context ≤ 16384 tokens · Maximum output 16384 tokens	131,072	Text output
DeepSeek V4.1 Flash 1017	USD 0.028 / 1M tokens · Quantization fp4	USD 0.4 / 1M tokens · Quantization fp4	1,000,000	Text output · Reasoning · Tool calling
Mistral Large 4	USD 0.544 / 1M tokens	USD 1.672 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
LongCat-2.5-Preview	USD 0.6 / 1M tokens	USD 2.36 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Ember-1	USD 2.4 / 1M tokens	USD 12 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 131,072
Maximum output: 16,384
Release date: 2025-10-16
Attachments: Yes
Reasoning: No
Tool calling: No
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is PaddleOCR VL for?

Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts

What inputs and outputs does PaddleOCR VL support?

Recorded inputs: text, images; outputs: text.

How is PaddleOCR VL priced?

The pricing table shows the current recorded Moduck price. For example: Input · Context ≤ 16384 tokens · Maximum output 16384 tokens USD 0.016 / 1M tokens; Output · Context ≤ 16384 tokens · Maximum output 16384 tokens USD 0.016 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for PaddleOCR VL?

Current model records list Context window 131,072 tokens; Maximum output 16,384 tokens.

What model parameter does the Quickstart use?

The example uses paddlepaddle/paddleocr-vl. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

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.