首页/GLM-OCR
ChatGLM

GLM-OCR

zai-org/glm-ocr
GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, achieving SOTA performance with a score of 94.62 on OmniDocBench V1.5. Optimized for real-world business scenarios, it delivers high-precision recognition for handwritten text, stamps, and code documentation. The model supports directly rendering complex tables into HTML code and extracting structured data from IDs and receipts into standard JSON format, enabling high-accuracy document parsing with minimal resource consumption.
价格
输入$0.03/百万 tokens
输出$0.03/百万 tokens

使用以下代码示例来集成我们的API:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.jiekou.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="zai-org/glm-ocr",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=32000,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

信息

提供商
量化
-

支持的功能

上下文长度
32000
最大输出
32000
serverless
支持
结构化输出
支持
Input Capabilities
text, image
Output Capabilities
text
联系我们