Layout Parsing

Use the GLM-OCR model to parse the layout of documents and images and extract text content. Support OCR recognition of images and PDF documents, returning detailed layout information and visualization results.

POST /paas/v4/layout_parsing

Layout Parsing

cURL

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

import requests

url = "https://api.z.ai/api/paas/v4/layout_parsing"

payload = {
    "model": "glm-ocr",
    "file": "https://cdn.bigmodel.cn/static/logo/introduction.png"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: 'glm-ocr', file: 'https://cdn.bigmodel.cn/static/logo/introduction.png'})
};

fetch('https://api.z.ai/api/paas/v4/layout_parsing', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

HttpResponse<String> response = Unirest.post("https://api.z.ai/api/paas/v4/layout_parsing")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"glm-ocr\",\n  \"file\": \"https://cdn.bigmodel.cn/static/logo/introduction.png\"\n}")
  .asString();

200

{
  "id": "task_123456789",
  "created": 1727156815,
  "model": "GLM-OCR",
  "md_results": "# Doc title\nThis is the document content...",
  "layout_details": [
    [
      {
        "index": 1,
        "label": "text",
        "bbox_2d": [
          0.1,
          0.1,
          0.5,
          0.3
        ],
        "content": "This is the content of the element",
        "height": 800,
        "width": 600
      }
    ]
  ],
  "layout_visualization": [
    "<string>"
  ],
  "data_info": {
    "num_pages": 5,
    "pages": [
      {
        "width": 600,
        "height": 800
      }
    ]
  },
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123
    },
    "total_tokens": 123
  },
  "request_id": "req_123456789"
}

{
  "code": 123,
  "message": "<string>"
}

Authorizations

Authorization · string · header · required

Use the following format for authentication: Bearer

Body

application/json

model · enum<string> · required

Model code: glm-ocr

Available options: glm-ocr

Example:

"glm-ocr"

file · string · required

Image or PDF document to be recognized, supports URL and base64. Supported image formats: PDF, JPG, PNG. Single image ≤10MB, PDF ≤50MB, maximum support 30 pages

Example:

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

return_crop_images · boolean · default: false

Whether to return screenshot information

need_layout_visualization · boolean · default: false

Whether to return detailed layout image result information

start_page_id · integer

Start page number for parsing when PDF is provided

Required range: x >= 1

end_page_id · integer

End page number for parsing when PDF is provided

Required range: x >= 1

request_id · string

Passed by the user side, needs to be unique; used to distinguish each request, 6–64 characters. If not provided by the user side, the platform will generate one by default.

Required string length: 6 - 64

user_id · string

Unique ID for the end user, 6–128 characters. Avoid using sensitive information.

Required string length: 6 - 128

Response

200

application/json

Business processing successful

id · string · required

Task ID

Example:

"task_123456789"

created · integer<int64> · required

Request creation time, Unix timestamp in seconds

Example:

1727156815

model · string · required

Model name

Example:

"GLM-OCR"

md_results · string

Recognition result in Markdown format

Example:

"# Doc title\nThis is the document content..."

layout_details · object[][]

Detailed layout information

Hide child attributes

layout_details. index · integer · required

Element index

Example:

1

layout_details. label · enum<string> · required

Element type: image for images, text for text content, formula for inline formulas, table for tables

Available options: image, text, formula, table

Example:

"text"

layout_details. bbox_2d · number[]

Normalized element coordinates [x1,y1,x2,y2]

Required array length: 4 elements

Required range: 0 <= x <= 1

Example:

[0.1, 0.1, 0.5, 0.3]

layout_details. content · string

Element content (text / image URL / table HTML)

Example:

"This is the content of the element"

layout_details. height · integer

Page height

Example:

800

layout_details. width · integer

Page width

Example:

600

layout_visualization · string[]

Recognition result image URLs

data_info · object

Document basic information

Hide child attributes

data_info. num_pages · integer · required

Total number of document pages

Example:

5

data_info. pages · object[]

Document page count information

Hide child attributes

data_info.pages. width · integer · required

Page width

Example:

600

data_info.pages. height · integer · required

Page height

Example:

800

usage · object

Token usage statistics returned when the model call ends.

Hide child attributes

usage. prompt_tokens · number

Number of tokens in user input

usage. completion_tokens · number

Number of output tokens

usage. prompt_tokens_details · object

Hide child attributes

usage.prompt_tokens_details. cached_tokens · number

Number of tokens served from cache

usage. total_tokens · integer

Total number of tokens

request_id · string

Request ID

Example:

"req_123456789"