Zhipu AI

GLM-OCR

About

GLM-OCR is a 0.9B open-weight model from Zhipu AI. Compact multilingual document OCR and markdown extraction. It accepts text, images, and documents. Context window is 8K. Released January 30, 2026.

Parameters
0.9B
Published parameter count.
Context window
8K
Tokens of context on a request.
License
MIT
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	$0.10
Cached input / 1M	$0.02
Output / 1M	$0.20

Compare

GLM-OCR 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
GLM-OCR	Compact multilingual document OCR and markdown extraction.	$0.10 / 1M input	0.9B	8K
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
dots.mocr	Multilingual document layout parsing and markdown OCR.	$0.20 / 1M input	3B	32K

Benchmarks

Published scores for GLM-OCR, from the OmniDocBench leaderboard.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	OmniDocBench v1.6: 95.22.
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
235 ms
Throughput
601 tok/s
Requests
120

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.

markdown is the only method: a Markdown / HTML string for an image and for each page of a PDF.
Context window 8,192 tokens, with a maximum output of 8,192 tokens.
Aliases: glm-ocr, zai-org/GLM-OCR. Weights: zai-org/GLM-OCR.

Methods

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

Method	Returns
markdown (default)	Reading-order Markdown / HTML string

Text mode emits the string alone for one image, and one <document> / <page> block per PDF, each page carrying format="markdown". In JSON mode an image content is the string, and a document page content is doc.page.blocks. See Methods & Response Format.

Estimate cost

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

Pages

$0.45

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="zai-org/glm-ocr",
    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.

A single image returns the Markdown string alone, with no wrapper.