RedNote HiLab: dots.ocr
rednote-hilab/dots.ocr
Access dots.ocr from RedNote HiLab using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "rednote-hilab/dots.ocr"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "rednote-hilab/dots.ocr"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="rednote-hilab/dots.ocr",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "rednote-hilab/dots.ocr",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
dots.ocr is a multilingual document-parsing vision-language model built by rednote-hilab, the AI research lab behind RedNote (Xiaohongshu).
It pairs a 1.2B-parameter vision encoder with a compact 1.7B-parameter language model (Qwen2.5-1.5B), and handles layout detection, text recognition, table extraction, formula recognition, and reading-order prediction in one model, switching between these tasks through prompt changes rather than separate specialized pipelines.
On OmniDocBench, it reports a 0.032 edit distance for English text recognition and 88.6/89.0 TEDS scores for English/Chinese table extraction, and its authors say it outperforms Gemini 2.5 Pro and Doubao-1.5-thinking-vision-pro on several metrics despite fewer parameters. It also beats DocLayout-YOLO on layout detection (F1 0.845 vs 0.733).
It covers 100 languages, including low-resource scripts, and has been officially integrated into vLLM since version 0.11.0. It suits developers who need one API call to parse mixed-language academic papers, financial reports, or scanned forms without stitching together separate detection and recognition models.
Context Window 131K
tokens
Max Output 131K
tokens
Input Cost $0.01
per million tokens
Output Cost $0.01
per million tokens
Release Date N/A
Model Playground
Try dots.ocr instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access dots.ocr by RedNote HiLab through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add dots.ocr to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.01 |
| Output | $0.01 |
dots.ocr supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
dots.ocr can generate up to 131K tokens in a single response.
Yes — the dots.ocr API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add dots.ocr to your app without worrying about API keys or setup.
Read the Docs View Tutorials