Skip to content

feat: add GLM-4.6V model support for z.ai provider - #4530

Merged
kevinvandijk merged 3 commits into
Kilo-Org:mainfrom
alvinward:feat/add-glm-4.6V-support
Dec 18, 2025
Merged

feat: add GLM-4.6V model support for z.ai provider#4530
kevinvandijk merged 3 commits into
Kilo-Org:mainfrom
alvinward:feat/add-glm-4.6V-support

Conversation

@alvinward

Copy link
Copy Markdown

Context

Added support for the new Zhipu AI (Z.AI) models:

  • GLM-4.6V
  • GLM-4.6V-Flash

Reference: https://docs.z.ai/guides/vlm/glm-4.6v

Implementation

Updated the configuration in packages/types/src/providers/zai.ts

Screenshots

Test configuration for GLM-4.6V
GLM-4 6V-Configuration

Test configuration for GLM-4.6V-Flash
GLM-4 6V-Flash-Configuration

Testing that GLM-4.6V works
GLM-4 6V-Test

Testing that GLM-4.6V-Flash works
GLM-4 6V-Flash-Test

How to Test

  • Configure a new Provider Profile
    • Profile Type: Chat
    • API Provider: Z.ai
    • Z AI Entrypoint: International
    • Model: glm-4.6v or glm-4.6v-flash
  • Select the new profile and in the prompt window and verify that you are receiving responses

Get in Touch

Discord handle: alvin_50005

@changeset-bot

changeset-bot Bot commented Dec 17, 2025

Copy link
Copy Markdown

🦋 Changeset detected

Latest commit: 782347e

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
kilo-code Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

@kevinvandijk

Copy link
Copy Markdown
Contributor

Thank you!

@johngsen

Copy link
Copy Markdown

Hi! can you add support for glm4.7?

@alvinward

Copy link
Copy Markdown
Author

Hi! can you add support for glm4.7?

It looks like somebody has already opened a pull request [#4628] for glm4.7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants