From 643229c3d5acd6253aa6501f9f70f2533b3edfd0 Mon Sep 17 00:00:00 2001 From: kevint-cerebras Date: Tue, 28 Oct 2025 19:39:00 -0700 Subject: [PATCH 1/4] feat: add zai-glm-4.6 model and update gpt-oss-120b for Cerebras - Add zai-glm-4.6 with 128K context window and 40K max tokens - Set zai-glm-4.6 as default Cerebras model - Update gpt-oss-120b to 128K context and 40K max tokens --- packages/types/src/providers/cerebras.ts | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/packages/types/src/providers/cerebras.ts b/packages/types/src/providers/cerebras.ts index 4765302a4e6..1c995071c23 100644 --- a/packages/types/src/providers/cerebras.ts +++ b/packages/types/src/providers/cerebras.ts @@ -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" 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, @@ -64,13 +73,12 @@ export const cerebrasModels = { supportsReasoningEffort: true, }, "gpt-oss-120b": { - maxTokens: 8000, - contextWindow: 64000, + maxTokens: 40000, + contextWindow: 128000, supportsImages: false, supportsPromptCache: false, inputPrice: 0, outputPrice: 0, - description: - "OpenAI GPT OSS model with ~2800 tokens/s\n\n• 64K context window\n• Excels at efficient reasoning across science, math, and coding", + description: "Intelligent general-purpose model with ~3000 tokens/s", }, } as const satisfies Record From 7e7c7fe25c1a7570831f13e33ac64132ae72b482 Mon Sep 17 00:00:00 2001 From: kevint-cerebras Date: Tue, 28 Oct 2025 19:41:52 -0700 Subject: [PATCH 2/4] feat: add zai-glm-4.6 model to Cerebras provider - Add zai-glm-4.6 with 128K context window and 40K max tokens - Set zai-glm-4.6 as default Cerebras model - Model provides ~2000 tokens/s for general-purpose tasks --- packages/types/src/providers/cerebras.ts | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/packages/types/src/providers/cerebras.ts b/packages/types/src/providers/cerebras.ts index 1c995071c23..7d5d517b422 100644 --- a/packages/types/src/providers/cerebras.ts +++ b/packages/types/src/providers/cerebras.ts @@ -73,12 +73,13 @@ export const cerebrasModels = { supportsReasoningEffort: true, }, "gpt-oss-120b": { - maxTokens: 40000, - contextWindow: 128000, + maxTokens: 8000, + contextWindow: 64000, supportsImages: false, supportsPromptCache: false, inputPrice: 0, outputPrice: 0, - description: "Intelligent general-purpose model with ~3000 tokens/s", + description: + "OpenAI GPT OSS model with ~2800 tokens/s\n\n• 64K context window\n• Excels at efficient reasoning across science, math, and coding", }, } as const satisfies Record From 2a31884aec460045b5202872aa55510b9e890692 Mon Sep 17 00:00:00 2001 From: kevint-cerebras Date: Wed, 29 Oct 2025 12:22:31 -0700 Subject: [PATCH 3/4] add [SOON TO BE DEPRECATED] warning for Q3C --- packages/types/src/providers/cerebras.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/types/src/providers/cerebras.ts b/packages/types/src/providers/cerebras.ts index 7d5d517b422..f5267936abc 100644 --- a/packages/types/src/providers/cerebras.ts +++ b/packages/types/src/providers/cerebras.ts @@ -23,7 +23,7 @@ export const cerebrasModels = { inputPrice: 0, outputPrice: 0, description: - "SOTA coding model with ~2000 tokens/s ($0 free tier)\n\n• Use this if you don't have a Cerebras subscription\n• 64K context window\n• Rate limits: 150K TPM, 1M TPH/TPD, 10 RPM, 100 RPH/RPD\n\nUpgrade for higher limits: [https://cloud.cerebras.ai/?utm=roocode](https://cloud.cerebras.ai/?utm=roocode)", + "[SOON TO BE DEPRECATED] SOTA coding model with ~2000 tokens/s ($0 free tier)\n\n• Use this if you don't have a Cerebras subscription\n• 64K context window\n• Rate limits: 150K TPM, 1M TPH/TPD, 10 RPM, 100 RPH/RPD\n\nUpgrade for higher limits: [https://cloud.cerebras.ai/?utm=roocode](https://cloud.cerebras.ai/?utm=roocode)", }, "qwen-3-coder-480b": { maxTokens: 40000, @@ -33,7 +33,7 @@ export const cerebrasModels = { inputPrice: 0, outputPrice: 0, description: - "SOTA coding model with ~2000 tokens/s ($50/$250 paid tiers)\n\n• Use this if you have a Cerebras subscription\n• 131K context window with higher rate limits", + "[SOON TO BE DEPRECATED] SOTA coding model with ~2000 tokens/s ($50/$250 paid tiers)\n\n• Use this if you have a Cerebras subscription\n• 131K context window with higher rate limits", }, "qwen-3-235b-a22b-instruct-2507": { maxTokens: 64000, From d360eb92768ec73b1b8d2c00a79f96f9da9c402e Mon Sep 17 00:00:00 2001 From: kevint-cerebras Date: Wed, 29 Oct 2025 12:25:32 -0700 Subject: [PATCH 4/4] chore: set gpt-oss-120b as default Cerebras model --- packages/types/src/providers/cerebras.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/types/src/providers/cerebras.ts b/packages/types/src/providers/cerebras.ts index f5267936abc..93aa7918f66 100644 --- a/packages/types/src/providers/cerebras.ts +++ b/packages/types/src/providers/cerebras.ts @@ -3,7 +3,7 @@ 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 = "zai-glm-4.6" +export const cerebrasDefaultModelId: CerebrasModelId = "gpt-oss-120b" export const cerebrasModels = { "zai-glm-4.6": {