scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-09-10 22:41:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: update Cerebras maxTokens to 16384 (#10387)

Browse source
This commit is contained in:
Seb Duerr 2025-12-29 19:56:59 -08:00 • committed by GitHub
parent c193f59819
commit 19b7dac719
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
packages/types/src/providers/cerebras.ts
View file

@ -7,7 +7,7 @@ export const cerebrasDefaultModelId: CerebrasModelId = "gpt-oss-120b"
export const cerebrasModels = {
"zai-glm-4.6": {
maxTokens: 8192, // Conservative default to avoid premature rate limiting (Cerebras reserves quota upfront)
maxTokens: 16384, // Conservative default to avoid premature rate limiting (Cerebras reserves quota upfront)
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
@ -18,7 +18,7 @@ export const cerebrasModels = {
description: "Highly intelligent general purpose model with up to 1,000 tokens/s",
},
"qwen-3-235b-a22b-instruct-2507": {
maxTokens: 8192, // Conservative default to avoid premature rate limiting
maxTokens: 16384, // Conservative default to avoid premature rate limiting
contextWindow: 64000,
supportsImages: false,
supportsPromptCache: false,
@ -29,7 +29,7 @@ export const cerebrasModels = {
description: "Intelligent model with ~1400 tokens/s",
},
"llama-3.3-70b": {
maxTokens: 8192, // Conservative default to avoid premature rate limiting
maxTokens: 16384, // Conservative default to avoid premature rate limiting
contextWindow: 64000,
supportsImages: false,
supportsPromptCache: false,
@ -40,7 +40,7 @@ export const cerebrasModels = {
description: "Powerful model with ~2600 tokens/s",
},
"qwen-3-32b": {
maxTokens: 8192, // Conservative default to avoid premature rate limiting
maxTokens: 16384, // Conservative default to avoid premature rate limiting
contextWindow: 64000,
supportsImages: false,
supportsPromptCache: false,
@ -51,7 +51,7 @@ export const cerebrasModels = {
description: "SOTA coding performance with ~2500 tokens/s",
},
"gpt-oss-120b": {
maxTokens: 8192, // Conservative default to avoid premature rate limiting
maxTokens: 16384, // Conservative default to avoid premature rate limiting
contextWindow: 64000,
supportsImages: false,
supportsPromptCache: false,