[Feature]: Add support for GLM-OCR model

[Huaweidev]

Issue Checklist

• I understand that issues are for reporting problems and requesting features, not for off-topic comments, and I will provide as much detail as possible to help resolve the issue.
• I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
• I have provided a short and descriptive title so that developers can quickly understand the issue when browsing the issue list, rather than vague titles like "A suggestion" or "Stuck."
• The latest version of Cherry Studio does not include the feature I am suggesting.

Platform

Windows

Version

v1.7.15

Is your feature request related to an existing issue?

N/A

Desired Solution

Currently, the GLM-OCR model manually added on the Zhipu Open Platform reports errors during both text and image conversations, even though the "Model Type: Visual" option has been enabled in the model settings.

响应首部: {
  "date": "Thu, 05 Feb 2026 01:42:27 GMT",
  "document-policy": "include-js-call-stacks-in-crash-reports",
  "strict-transport-security": "max-age=31536000; includeSubDomains",
  "vary": "Origin, Access-Control-Request-Method, Access-Control-Request-Headers, Origin, Access-Control-Request-Method, Access-Control-Request-Headers",
  "x-log-id": "20260205094226184d5f25e9264aa9"
}
响应内容: {
  "error": {
    "code": "1214",
    "message": "OCR仅支持PDF、JPG、PNG格式；文件大小限制：图片≤10MB、PDF≤50MB；PDF最大100页"

Alternative Solutions

N/A

Additional Information

You can get normal output using the following command.

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

Output content:

created              : 1770255532
data_info            : @{num_pages=1; pages=System.Object[]}
id                   : 20260205093850e5c25b10db3d44d6
layout_details       : {                                   }
layout_visualization : {}
md_results           : 模型体验
                       文本模型
...
...

[black-jack911]

Note

This comment was translated by Claude.

This model currently performs well with OCR. Would you consider adding a document processing module?

---

Original Content

该模型目前ocr效果良好 是否可以考虑加入文档处理模块