feat: add GLM-4.6 model support to Z.AI provider #8412
Closed
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
- Add glm-4.6 model to both international and mainland Z.AI configurations - Update model to GLM-4.6 as default for both regions - Configure 200K context window (upgraded from 131K in GLM-4.5) - Add tiered pricing for mainland China (32K, 128K, 200K+ contexts) - Support 355B-parameter MoE architecture with improved capabilities - Enable prompt caching support for cost optimization GLM-4.6 represents Zhipu's latest SOTA model with significant improvements in coding, reasoning, search, writing, and agent applications across 8 authoritative benchmarks.
dosubot
bot
added
size:M
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
| cacheWritesPrice: 0, | ||
| cacheReadsPrice: 0.11, | ||
| description: | ||
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
There was a problem hiding this comment.
Typo: In the GLM-4.6 description, 'agentsUpgraded' is missing a separator (e.g. a space or punctuation).
Suggested change
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", | |
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agents, upgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
| cacheWritesPrice: 0, | ||
| cacheReadsPrice: 0.057, | ||
| description: | ||
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
There was a problem hiding this comment.
Typo: In the GLM-4.6 description for the Mainland model, 'agentsUpgraded' is missing a separator.
Suggested change
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", | |
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agents, Upgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
| cacheWritesPrice: 0, | ||
| cacheReadsPrice: 0.11, | ||
| description: | ||
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
There was a problem hiding this comment.
P2: Typo/grammar. Missing space in 'agentsUpgraded' and plural 'models' should be singular. Add 'window' for clarity.
Suggested change
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", | |
| \"GLM-4.6 is Zhipu's latest SOTA model for reasoning, coding, and agents. Upgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and a 200K context window, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.\", |
| cacheWritesPrice: 0, | ||
| cacheReadsPrice: 0.057, | ||
| description: | ||
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", |
There was a problem hiding this comment.
P2: Same copy issue as above.
Suggested change
| "GLM-4.6 is Zhipu's latest SOTA models for reasoning, code, and agentsUpgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and 200K context, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.", | |
| \"GLM-4.6 is Zhipu's latest SOTA model for reasoning, coding, and agents. Upgraded across 8 authoritative benchmarks. With a 355B-parameter MoE architecture and a 200K context window, it surpasses GLM-4.5 in coding, reasoning, search, writing, and agent applications.\", |
| cacheReadsPrice: 0.057, | ||
| }, | ||
| { | ||
| contextWindow: Infinity, |
There was a problem hiding this comment.
P2: Using Infinity for a tier contextWindow can cause issues in some consumers (JSON serialization, numeric comparisons). Given the model’s max supported context is 200K, use explicit numeric value.
Suggested change
| contextWindow: Infinity, | |
| contextWindow: 200_000, |
hannesrudolph
added
the
Issue/PR - Triage
Collaborator
|
Thank you for the PR! Didn't have permission to make edits so went with #8408, but let me know if you see anything that got missed. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
GLM-4.6 represents Zhipu's latest SOTA model with significant improvements in coding, reasoning, search, writing, and agent applications across 8 authoritative benchmarks.
Related GitHub Issue
Closes: # 8406
Roo Code Task Context (Optional)
Description
Add support for GLM-4.6, Zhipu AI's latest SOTA model, to the Z.AI provider. This update makes GLM-4.6 the default model for both international and mainland China configurations.
Test Procedure
[x] All existing tests pass (15/15 tests green)
[x] Type checking passes
[x] Linting passes
[x] Build succeeds
[x] Extension packaged successfully
Pre-Submission Checklist
Documentation Updates
Additional Notes
Important
Add support for GLM-4.6 model to Z.AI provider, updating default model, context window, pricing, and enabling prompt caching.
GLM-4.6model tointernationalZAiModelsandmainlandZAiModelsinzai.ts.GLM-4.6as default model for both international and mainland China.GLM-4.5.This description was created by
for 1339c7c. You can customize this summary. It will automatically update as commits are pushed.