GLM-OCR

Overview

GLM-OCR is a lightweight professional OCR model with parameters as small as 0.9B, yet it achieves state-of-the-art performance across multiple capabilities. It sets a new benchmark for document parsing with its “small size and high accuracy.” Key features include:

• Performance SOTA: Scored 94.62 points to top OmniDocBench V1.5 and achieved current best performance across multiple mainstream document understanding benchmarks including tables and formulas at launch.
• Optimized for Real-World Scenarios: Delivers stable, leading accuracy in complex environments like code documentation, intricate tables, and stamp recognition. Maintains exceptional recognition precision even with complex layouts, diverse fonts, or mixed text-image content.
• Efficient and Cost-Effective: With just 0.9B parameters, supports VLLM and SGLang deployment, significantly reducing inference latency and computational overhead.

Input Modality

• PDF, images (JPG, PNG)
• Single image ≤ 10MB, PDF ≤ 50MB
• Maximum support: 100 pages

Output Modality

Text / Image Links / MD Documents

Supported Language

Support Chinese, English, French, Spanish, Russian, German, Japanese, Korean, etc.

For detailed pricing information on GLM-OCR, please visit the Pricing Page.

Usage

Text Recognition

Recognize text content from photos, screenshots, documents, and scans, supporting printed text, handwriting, and mathematical formulas. Applicable to diverse scenarios including education, research, and office work.

Table Recognition

Identify table structures and content, converting them into HTML-formatted sequences. Suitable for scenarios involving table data entry, conversion, and editing.

Information Structuring

Extract key information from various cards, certificates, receipts, and forms, outputting structured JSON data. Supports applications in banking, insurance, government services, legal, logistics, and other industries.

Retrieval-Augmented Generation (RAG)

Support high-volume document recognition and parsing with high accuracy and standardized output formats, providing a robust foundation for RAG.

Resources

• API Documentation: Learn how to call the API.

Introducing GLM-OCR

1. State-of-the-Art Performance, Precision in Action

   Thanks to its proprietary CogViT visual encoder and deep scene optimization, GLM-OCR achieves “compact size, high accuracy.”

   With only 0.9B parameters, GLM-OCR achieved SOTA on the authoritative document parsing benchmark OmniDocBench V1.5 with a score of 94.6. It outperforms multiple specialized OCR models across four key domains—text, formula, table recognition, and information extraction—with performance approaching that of Gemini-3-Pro.

   

   Beyond public benchmarks, we conducted internal evaluations across six core real-world scenarios. Results show GLM-OCR delivers significant advantages across dimensions including code documentation, real-world tables, handwriting, multilingual text, seal recognition, and invoice extraction.

   

2. Faster, More Cost-Effective

   For speed, we compared different OCR methods under identical hardware and testing conditions (single replica, single concurrency), evaluating their performance in parsing and exporting Markdown files from both image and PDF inputs. Results show GLM-OCR achieves a throughput of 1.86 pages/second for PDF documents and 0.67 images/second for images, significantly outperforming comparable models.

   

   Pricing is uniform for both API input and output, costing just $0.03 per million tokens.

Examples

Code Block Recognition

Input

Output

Complex Chart Content Recognition

Input

Output

Bill Recognition

Input

Output

Handwriting Recognition

Input

Output

Quick Start

cURL

curl --location --request POST 'https://api.z.ai/api/paas/v4/layout_parsing' \
--header 'Authorization: Bearer your-api-key' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "glm-ocr",
  "file": "https://cdn.bigmodel.cn/static/logo/introduction.png"
}'

Python

Install SDK

# Install the latest version
pip install zai-sdk
# Or specify a version
pip install zai-sdk==0.2.3

Verify installation

import zai
print(zai.__version__)

Basic Call

from zai import ZaiClient

# Initialize client
client = ZaiClient(api_key="your-api-key")

image_url = "https://cdn.bigmodel.cn/static/logo/introduction.png"

# Call layout parsing API
response = client.layout_parsing.create(
    model="glm-ocr",
    file=image_url
)

# Output result
print(response)

Java

Install SDK

Maven

<dependency>
  <groupId>ai.z.openapi</groupId>
  <artifactId>zai-sdk</artifactId>
  <version>0.3.5</version>
</dependency>

Gradle (Groovy)

implementation 'ai.z.openapi:zai-sdk:0.3.5'

Basic Call

import ai.z.openapi.ZaiClient;
import ai.z.openapi.service.layoutparsing.LayoutParsingCreateParams;
import ai.z.openapi.service.layoutparsing.LayoutParsingResponse;
import ai.z.openapi.service.layoutparsing.LayoutParsingResult;

public class LayoutParsing {
    public static void main(String[] args) {
        // Initialize client
        ZaiClient client = ZaiClient.builder()
            .ofZAI()
            .apiKey("your-api-key")
            .build();

        String model = "glm-ocr";
        String file = "https://cdn.bigmodel.cn/static/logo/introduction.png";

        // Create layout parsing request
        LayoutParsingCreateParams params = LayoutParsingCreateParams.builder()
            .model(model)
            .file(file)
            .build();

        // Send request
        LayoutParsingResponse response = client.layoutParsing().layoutParsing(params);

        // Handle response
        if (response.isSuccess()) {
            System.out.println("Parsing result: " + response.getData());
        } else {
            System.err.println("Error: " + response.getMsg());
        }
    }
}