feat(models): add GLM vision Flash models to Z.AI curated list - #46562
Closed
Icather wants to merge 2 commits into
Closed
feat(models): add GLM vision Flash models to Z.AI curated list#46562Icather wants to merge 2 commits into
Icather wants to merge 2 commits into
Conversation
Add glm-4.6v-flash, glm-4v-flash, and glm-4.1v-thinking-flash to the Z.AI / GLM provider curated model list. These are free-tier vision models suitable for auxiliary vision tasks (computer_use SOM screenshots, image analysis) with the following characteristics: - glm-4.6v-flash: latest Flash vision, concurrency=1 (free) - glm-4v-flash: stable vision, concurrency=10 (free) - glm-4.1v-thinking-flash: thinking+vision, concurrency=5 (free) Previously only glm-5/4 text models and glm-5v-turbo were listed, making the free vision Flash models unavailable in the Dashboard model selector.
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds additional GLM vision model IDs to the curated model list so they’re available to Hermes users.
Changes:
- Added three GLM free-tier vision model identifiers to the curated provider model list.
- Documented the intended tier/limits for the newly added models via an inline comment.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Icather
commented
Jun 15, 2026
Icather
left a comment
Icather
left a comment
Contributor
Author
There was a problem hiding this comment.
Fixed in 9a4b33c: reordered by version descending and removed the operational comment. Ready for re-review.
Comprehensive model list covering text, vision, and Flash tiers:
Text models: glm-5.2, 5.1, 5, 5-turbo, 4.7, 4.7-flash, 4.6,
4.5, 4.5-flash, 4-flash-250414
Vision models: glm-5v-turbo, 4.6v, 4.6v-flash, 4.5v, 4v, 4v-flash
Thinking: glm-4.1v-thinking, 4.1v-thinking-flash
Ordered by version descending. Comment about concurrency limits
removed — this is provider policy, not enforced by Hermes.
alt-glitch
added
type/feature
12 tasks
Contributor
Author
|
Superseded by #46724, which fixes the underlying issue (API endpoint routing + free model visibility) rather than just expanding the curated list. Closing in favor of that PR. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds three free-tier Z.AI / GLM vision models to the curated model list so they appear in the Dashboard model selector:
glm-4.6v-flashglm-4v-flashglm-4.1v-thinking-flashWhy
Currently the Z.AI provider only lists text models (
glm-5,glm-4.7, etc.) andglm-5v-turbo. The free vision Flash models are available via the Z.AI API but invisible in the UI — users can't select them as auxiliary vision models for computer_use screenshots or image analysis.Testing