文档解析

使用 GLM-OCR 模型解析文档和图片的布局并提取文本内容。支持图片和PDF文档的OCR识别，返回详细的布局信息和可视化结果。点击 Try it 按钮可快速试用。

POST /paas/v4/layout_parsing

文档解析

cURL

curl --request POST \
  --url https://open.bigmodel.cn/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://open.bigmodel.cn/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://open.bigmodel.cn/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://open.bigmodel.cn/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();

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://open.bigmodel.cn/api/paas/v4/layout_parsing"

	payload := strings.NewReader("{\n  \"model\": \"glm-ocr\",\n  \"file\": \"https://cdn.bigmodel.cn/static/logo/introduction.png\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://open.bigmodel.cn/api/paas/v4/layout_parsing",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'glm-ocr',
    'file' => 'https://cdn.bigmodel.cn/static/logo/introduction.png'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

200

{
  "id": "task_123456789",
  "created": 1727156815,
  "model": "GLM-OCR",
  "md_results": "# 文档标题\n这是文档内容...",
  "layout_details": [
    [
      {
        "index": 1,
        "label": "text",
        "bbox_2d": [
          0.1,
          0.1,
          0.5,
          0.3
        ],
        "content": "这是文本内容",
        "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"
}

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

Authorizations

Authorization · string · header · required

标准的 HTTP Bearer 认证方式，在 API Keys 页面获取密钥。

Body

application/json

model · enum<string> · required

模型编码：glm-ocr

Available options: glm-ocr

Example:

"glm-ocr"

file · string · required

需要识别的图片或者pdf文档，支持url和base64。支持图片格式：PDF、JPG、PNG。单图≤10MB，PDF≤50MB，最大支持100页

Example:

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

return_crop_images · boolean · default: false

是否需要截图信息

need_layout_visualization · boolean · default: false

是否需要详细布局图片结果信息

start_page_id · integer

传入pdf时，开始解析的页码

Required range: x >= 1

end_page_id · integer

传入pdf时，结束解析的页码

Required range: x >= 1

request_id · string

请求唯一标识符。由用户端传递，ID长度要求：最少6个字符，最多64个字符，建议使用UUID格式确保唯一性，若未提供平台将自动生成。

Required string length: 6 - 64

user_id · string

终端用户ID，用于滥用监控。长度：6-128字符

Required string length: 6 - 128

Example:

"user_123456"

Response

200

application/json

业务处理成功

id · string · required

任务 ID

Example:

"task_123456789"

created · integer<int64> · required

请求创建时间，是以秒为单位的 Unix 时间戳

Example:

1727156815

model · string · required

模型名称

Example:

"GLM-OCR"

md_results · string

Markdown 格式的识别结果

Example:

"# 文档标题\n这是文档内容..."

layout_details · object[][]

布局详细信息

Show child attributes

layout_visualization · string[]

识别结果图片url

data_info · object

文档基础信息

Show child attributes

usage · object

调用结束时返回的 Token 使用统计。

Show child attributes

request_id · string

请求ID

Example:

"req_123456789"