rednote-hilab

dots.mocr

About

dots.mocr is a 3B open-weight model from rednote-hilab. Multilingual document layout parsing and markdown OCR. It accepts text, images, and documents. Context window is 32K. Released March 19, 2026.

Parameters
3B
Published parameter count.
Context window
32K
Tokens of context on a request.
License
Apache-2.0
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$0.20
Cached input / 1M	$0.03
Output / 1M	$0.40

Compare

dots.mocr is one of the catalog's OCR models. The table is each model's published price, size, and context.

Model	What it does	Price	Parameters	Context
dots.mocr	Multilingual document layout parsing and markdown OCR.	$0.20 / 1M input	3B	32K
PP-OCRv6	PaddleOCR PP-OCRv6 medium text detection and recognition; scene OCR JSONL on image chat; text returns plain text; document_url fan-out via text.	$0.02 / 1M input	20M	—
DeepSeek-OCR-2	DeepSeek OCR 2 and markdown extraction.	$0.25 / 1M input	3.4B	32K
GLM-OCR	Compact multilingual document OCR and markdown extraction.	$0.10 / 1M input	0.9B	8K

Benchmarks

Published scores for dots.mocr, from the Infinity-Parser2 technical report.

Evals

ParseBench55.8

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	ParseBench: 55.8.
Cost and performance	Lower listed rate, mid-pack latency

Performance

Latency is the end-to-end round trip. Throughput is completion tokens divided by that time. It is a request rate, not decode speed.

Latency
2,182 ms
Throughput
—
Requests
308

Supported inputs

textIgnored
A text part beside the media is accepted and ignored. A request with no media part is a 400.
image_urlYes
One per request. A second image_url part is a 400.
video_urlNo
Not accepted.
document_urlYes
One PDF, up to 128 pages, rasterized per page at document_dpi (default 96). See Document Inputs.

Default method markdown. parse_layout and parse_layout_only emit layout regions; ocr and markdown emit strings.
Context window 32,768 tokens, with a maximum output of 16,384 tokens.
Alias: dots.mocr. Weights: rednote-hilab/dots.mocr.

Methods

Methods this model serves. Payload shapes are in the docs.

Method	Returns
markdown	Reading-order Markdown string (default)
ocr	Plain OCR text
parse_layout	Region items with `bbox_xywh`, `label`, `text`
parse_layout_only	Region items with `bbox_xywh` and `label`, no text

The payload kind is the same for an image and for each page of a PDF. Text mode emits the payload alone for one image, and one <document> / <page> block per PDF, each page declaring its kind in format. In JSON mode an image content is the tagged container above, and a document page content is always doc.page.blocks. Coordinates are normalized 0-1 at precision decimals (default 4). See Methods & Response Format.

Estimate cost

Estimate. A page is 2,500 input tokens and 1,000 output tokens.

Pages

$0.90

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="rednote-hilab/dots.mocr",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document_url",
                    "document_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
                    },
                },
            ],
        }
    ],
    extra_body={"method": "markdown"},
)

print(response.choices[0].message.content)

Response

One <document> block per PDF, one <page> block per page. A failed page is self-closing, with status="error" and no body:

tsla-8k.pdf2 pages

Page 0

Annual Report 2024

Overview

The company reported revenue of $1.2M.

Page 1 · failed

This page returned no body.

With method="parse_layout" each page body is the block container instead, and the page carries format="json".