Update Cerebras models

.changeset/clever-elephants-unite.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Add new Cerebras models + update rate limits

src/api/providers/cerebras.ts

@@ -102,6 +102,7 @@ export class CerebrasHandler implements ApiHandler {
 				messages: cerebrasMessages,
 				temperature: 0,
 				stream: true,
+				max_tokens: this.getModel().info.maxTokens,
 			})
 
 			// Handle streaming response
@@ -175,9 +176,15 @@ export class CerebrasHandler implements ApiHandler {
 	}
 
 	getModel(): { id: string; info: ModelInfo } {
-		const modelId = this.options.apiModelId
-		if (modelId && modelId in cerebrasModels) {
-			const id = modelId as CerebrasModelId
+		const originalModelId = this.options.apiModelId
+		let apiModelId = originalModelId
+		if (originalModelId === "qwen-3-coder-480b-free") {
+			apiModelId = "qwen-3-coder-480b"
+			return { id: apiModelId, info: cerebrasModels[originalModelId as CerebrasModelId] }
+		}
+
+		if (originalModelId && originalModelId in cerebrasModels) {
+			const id = originalModelId as CerebrasModelId
 			return { id, info: cerebrasModels[id] }
 		}
 		return {

src/shared/api.ts

@@ -2480,8 +2480,28 @@ export const sambanovaModels = {
 // Cerebras
 // https://inference-docs.cerebras.ai/api-reference/models
 export type CerebrasModelId = keyof typeof cerebrasModels
-export const cerebrasDefaultModelId: CerebrasModelId = "qwen-3-235b-a22b-instruct-2507"
+export const cerebrasDefaultModelId: CerebrasModelId = "qwen-3-coder-480b-free"
 export const cerebrasModels = {
+	"qwen-3-coder-480b-free": {
+		maxTokens: 40000,
+		contextWindow: 64000,
+		supportsImages: false,
+		supportsPromptCache: false,
+		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=cline](https://cloud.cerebras.ai/?utm=cline)",
+	},
+	"qwen-3-coder-480b": {
+		maxTokens: 40000,
+		contextWindow: 128000,
+		supportsImages: false,
+		supportsPromptCache: false,
+		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",
+	},
 	"qwen-3-235b-a22b-instruct-2507": {
 		maxTokens: 64000,
 		contextWindow: 64000,
@@ -2509,9 +2529,9 @@ export const cerebrasModels = {
 		outputPrice: 0,
 		description: "SOTA coding performance with ~2500 tokens/s",
 	},
-	"qwen-3-235b-a22b": {
-		maxTokens: 40000,
-		contextWindow: 40000,
+	"qwen-3-235b-a22b-thinking-2507": {
+		maxTokens: 32000,
+		contextWindow: 65000,
 		supportsImages: false,
 		supportsPromptCache: false,
 		inputPrice: 0,