feat: add GLM-4.6V and GLM-4.6V-Flash models to Z.AI provider #123
Conversation
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
- Added GLM-4.6V with vision support, 131K context window, and 24K default max tokens - Added GLM-4.6V-Flash as a faster, lower-cost variant with 65K context - Both models support attachments for vision capabilities - Pricing reflects GLM-4.6V at $0.7/$2.5 per 1M tokens (in/out) - Flash variant is priced at 50% of standard V model cost - Maintains reasoning capabilities consistent with other GLM models This expands the Z.AI provider's multimodal offerings with the latest GLM vision models, enabling image processing alongside text reasoning. 💘 Generated with Crush Assisted-by: GLM-4.6 via Crush <[email protected]>
LarsArtmann
requested review from
raphamorim and
tauraamui
and removed request for
a team
- Update pricing for GLM-4.6V model: input cost reduced from $0.7 to $0.3 per 1M tokens, output cost reduced from $2.5 to $0.9 per 1M tokens, cached input cost reduced from $0.12 to $0.05 per 1M tokens - Update GLM-4.6V-Flash model: zero-cost pricing, increased context window from 65K to 131K tokens, increased default max tokens from 8K to 24K - Add catwalk CLI binary executable for local development and testing - Ensure consistency with latest provider pricing and capabilities 💘 Generated with Crush Assisted-by: DeepSeek: DeepSeek V3.2 via Crush <[email protected]>
Member
|
@LarsArtmann thanks for the PR, have you made sure that the changes work as expected in crush? You can test it locally by running the catwalk server This will help me validate the configuration too :) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Would be nice :)