feat: update Cerebras models (#9527)

Co-authored-by: Roo Code <[email protected]>

packages/types/src/providers/cerebras.ts

@@ -15,26 +15,6 @@ export const cerebrasModels = {
 		outputPrice: 0,
 		description: "Highly intelligent general purpose model with up to 1,000 tokens/s",
 	},
-	"qwen-3-coder-480b-free": {
-		maxTokens: 40000,
-		contextWindow: 64000,
-		supportsImages: false,
-		supportsPromptCache: false,
-		inputPrice: 0,
-		outputPrice: 0,
-		description:
-			"[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,
-		contextWindow: 128000,
-		supportsImages: false,
-		supportsPromptCache: false,
-		inputPrice: 0,
-		outputPrice: 0,
-		description:
-			"[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,
 		contextWindow: 64000,
@@ -62,16 +42,6 @@ export const cerebrasModels = {
 		outputPrice: 0,
 		description: "SOTA coding performance with ~2500 tokens/s",
 	},
-	"qwen-3-235b-a22b-thinking-2507": {
-		maxTokens: 40000,
-		contextWindow: 65000,
-		supportsImages: false,
-		supportsPromptCache: false,
-		inputPrice: 0,
-		outputPrice: 0,
-		description: "SOTA performance with ~1500 tokens/s",
-		supportsReasoningEffort: true,
-	},
 	"gpt-oss-120b": {
 		maxTokens: 8000,
 		contextWindow: 64000,

src/api/providers/cerebras.ts

@@ -98,19 +98,11 @@ export class CerebrasHandler extends BaseProvider implements SingleCompletionHan
 	}
 
 	getModel(): { id: CerebrasModelId; info: (typeof cerebrasModels)[CerebrasModelId] } {
-		const originalModelId = (this.options.apiModelId as CerebrasModelId) || this.defaultProviderModelId
-
-		// Route both qwen coder models to the same actual model ID for API calls
-		// This allows them to have different rate limits/descriptions in the UI
-		// while using the same underlying model
-		let apiModelId = originalModelId
-		if (originalModelId === "qwen-3-coder-480b-free") {
-			apiModelId = "qwen-3-coder-480b"
-		}
+		const modelId = (this.options.apiModelId as CerebrasModelId) || this.defaultProviderModelId
 
 		return {
-			id: apiModelId,
-			info: this.providerModels[originalModelId], // Use original model info for rate limits/descriptions
+			id: modelId,
+			info: this.providerModels[modelId],
 		}
 	}