Skip to content

Add zai glm model #8897

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

Add zai glm model #8897

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
643229c
feat: add zai-glm-4.6 model and update gpt-oss-120b for Cerebras
kevint-cerebras Oct 29, 2025
7e7c7fe
feat: add zai-glm-4.6 model to Cerebras provider
kevint-cerebras Oct 29, 2025
2a31884
add [SOON TO BE DEPRECATED] warning for Q3C
kevint-cerebras Oct 29, 2025
d360eb9
chore: set gpt-oss-120b as default Cerebras model
kevint-cerebras Oct 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion packages/types/src/providers/cerebras.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,18 @@ import type { ModelInfo } from "../model.js"
// https://inference-docs.cerebras.ai/api-reference/chat-completions
export type CerebrasModelId = keyof typeof cerebrasModels

export const cerebrasDefaultModelId: CerebrasModelId = "qwen-3-coder-480b-free"
export const cerebrasDefaultModelId: CerebrasModelId = "zai-glm-4.6"
Copy link

@roomote roomote bot Oct 29, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Setting this unreleased model as the default will break the Cerebras provider for all users until November 5th. According to the PR description, zai-glm-4.6 becomes available on November 5th, but this PR is being merged on October 29th. Users who select Cerebras as their provider will encounter API errors for approximately one week because the default model doesn't exist yet. Consider keeping qwen-3-coder-480b-free as the default until the new model is actually available on the platform.


export const cerebrasModels = {
"zai-glm-4.6": {
maxTokens: 40000,
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
description: "Highly intelligent general-purpose model with ~2000 tokens/s",
},
"qwen-3-coder-480b-free": {
maxTokens: 40000,
contextWindow: 64000,
Expand Down
Loading