feat: add support for Claude Opus 4.1 (claude-opus-4-1-20250805) (#6728)

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

.changeset/add-opus-4-1-model.md

@@ -0,0 +1,11 @@
+---
+"@roo-code/types": patch
+"roo-code": patch
+---
+
+Add support for Claude Opus 4.1 (claude-opus-4-1-20250805)
+
+- Added claude-opus-4-1-20250805 to anthropicModels with 8192 max tokens and reasoning budget support
+- Added support across all providers: Anthropic, Claude Code, Bedrock, Vertex AI, OpenRouter, and LiteLLM
+- Updated anthropic.ts provider to handle prompt caching for the new model
+- Pricing: $15/M input tokens, $75/M output tokens, $18.75/M cache writes, $1.5/M cache reads

packages/types/src/providers/anthropic.ts

@@ -18,6 +18,18 @@ export const anthropicModels = {
 		cacheReadsPrice: 0.3, // $0.30 per million tokens
 		supportsReasoningBudget: true,
 	},
+	"claude-opus-4-1-20250805": {
+		maxTokens: 8192,
+		contextWindow: 200_000,
+		supportsImages: true,
+		supportsComputerUse: true,
+		supportsPromptCache: true,
+		inputPrice: 15.0, // $15 per million input tokens
+		outputPrice: 75.0, // $75 per million output tokens
+		cacheWritesPrice: 18.75, // $18.75 per million tokens
+		cacheReadsPrice: 1.5, // $1.50 per million tokens
+		supportsReasoningBudget: true,
+	},
 	"claude-opus-4-20250514": {
 		maxTokens: 32_000, // Overridden to 8k if `enableReasoningEffort` is false.
 		contextWindow: 200_000,

packages/types/src/providers/bedrock.ts

@@ -82,6 +82,21 @@ export const bedrockModels = {
 		maxCachePoints: 4,
 		cachableFields: ["system", "messages", "tools"],
 	},
+	"anthropic.claude-opus-4-1-20250805-v1:0": {
+		maxTokens: 8192,
+		contextWindow: 200_000,
+		supportsImages: true,
+		supportsComputerUse: true,
+		supportsPromptCache: true,
+		supportsReasoningBudget: true,
+		inputPrice: 15.0,
+		outputPrice: 75.0,
+		cacheWritesPrice: 18.75,
+		cacheReadsPrice: 1.5,
+		minTokensPerCachePoint: 1024,
+		maxCachePoints: 4,
+		cachableFields: ["system", "messages", "tools"],
+	},
 	"anthropic.claude-opus-4-20250514-v1:0": {
 		maxTokens: 8192,
 		contextWindow: 200_000,

packages/types/src/providers/claude-code.ts

@@ -48,6 +48,14 @@ export const claudeCodeModels = {
 		supportsReasoningBudget: false,
 		requiredReasoningBudget: false,
 	},
+	"claude-opus-4-1-20250805": {
+		...anthropicModels["claude-opus-4-1-20250805"],
+		supportsImages: false,
+		supportsPromptCache: true, // Claude Code does report cache tokens
+		supportsReasoningEffort: false,
+		supportsReasoningBudget: false,
+		requiredReasoningBudget: false,
+	},
 	"claude-opus-4-20250514": {
 		...anthropicModels["claude-opus-4-20250514"],
 		supportsImages: false,

packages/types/src/providers/lite-llm.ts

@@ -17,6 +17,7 @@ export const litellmDefaultModelInfo: ModelInfo = {
 
 export const LITELLM_COMPUTER_USE_MODELS = new Set([
 	"claude-3-5-sonnet-latest",
+	"claude-opus-4-1-20250805",
 	"claude-opus-4-20250514",
 	"claude-sonnet-4-20250514",
 	"claude-3-7-sonnet-latest",
@@ -26,22 +27,26 @@ export const LITELLM_COMPUTER_USE_MODELS = new Set([
 	"vertex_ai/claude-3-5-sonnet-v2",
 	"vertex_ai/claude-3-5-sonnet-v2@20241022",
 	"vertex_ai/claude-3-7-sonnet@20250219",
+	"vertex_ai/claude-opus-4-1@20250805",
 	"vertex_ai/claude-opus-4@20250514",
 	"vertex_ai/claude-sonnet-4@20250514",
 	"openrouter/anthropic/claude-3.5-sonnet",
 	"openrouter/anthropic/claude-3.5-sonnet:beta",
 	"openrouter/anthropic/claude-3.7-sonnet",
 	"openrouter/anthropic/claude-3.7-sonnet:beta",
+	"anthropic.claude-opus-4-1-20250805-v1:0",
 	"anthropic.claude-opus-4-20250514-v1:0",
 	"anthropic.claude-sonnet-4-20250514-v1:0",
 	"anthropic.claude-3-7-sonnet-20250219-v1:0",
 	"anthropic.claude-3-5-sonnet-20241022-v2:0",
 	"us.anthropic.claude-3-5-sonnet-20241022-v2:0",
 	"us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+	"us.anthropic.claude-opus-4-1-20250805-v1:0",
 	"us.anthropic.claude-opus-4-20250514-v1:0",
 	"us.anthropic.claude-sonnet-4-20250514-v1:0",
 	"eu.anthropic.claude-3-5-sonnet-20241022-v2:0",
 	"eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
+	"eu.anthropic.claude-opus-4-1-20250805-v1:0",
 	"eu.anthropic.claude-opus-4-20250514-v1:0",
 	"eu.anthropic.claude-sonnet-4-20250514-v1:0",
 	"snowflake/claude-3-5-sonnet",

packages/types/src/providers/openrouter.ts

@@ -39,6 +39,7 @@ export const OPEN_ROUTER_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-3.7-sonnet:thinking",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-opus-4",
+	"anthropic/claude-opus-4.1",
 	"google/gemini-2.5-flash-preview",
 	"google/gemini-2.5-flash-preview:thinking",
 	"google/gemini-2.5-flash-preview-05-20",
@@ -59,6 +60,7 @@ export const OPEN_ROUTER_COMPUTER_USE_MODELS = new Set([
 	"anthropic/claude-3.7-sonnet:thinking",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-opus-4",
+	"anthropic/claude-opus-4.1",
 ])
 
 // When we first launched these models we didn't have support for
@@ -77,6 +79,7 @@ export const OPEN_ROUTER_REQUIRED_REASONING_BUDGET_MODELS = new Set([
 export const OPEN_ROUTER_REASONING_BUDGET_MODELS = new Set([
 	"anthropic/claude-3.7-sonnet:beta",
 	"anthropic/claude-opus-4",
+	"anthropic/claude-opus-4.1",
 	"anthropic/claude-sonnet-4",
 	"google/gemini-2.5-pro-preview",
 	"google/gemini-2.5-pro",

packages/types/src/providers/vertex.ts

@@ -175,6 +175,18 @@ export const vertexModels = {
 		cacheReadsPrice: 0.3,
 		supportsReasoningBudget: true,
 	},
+	"claude-opus-4-1@20250805": {
+		maxTokens: 8192,
+		contextWindow: 200_000,
+		supportsImages: true,
+		supportsComputerUse: true,
+		supportsPromptCache: true,
+		inputPrice: 15.0,
+		outputPrice: 75.0,
+		cacheWritesPrice: 18.75,
+		cacheReadsPrice: 1.5,
+		supportsReasoningBudget: true,
+	},
 	"claude-opus-4@20250514": {
 		maxTokens: 8192,
 		contextWindow: 200_000,

src/api/providers/anthropic.ts

@@ -47,6 +47,7 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
 
 		switch (modelId) {
 			case "claude-sonnet-4-20250514":
+			case "claude-opus-4-1-20250805":
 			case "claude-opus-4-20250514":
 			case "claude-3-7-sonnet-20250219":
 			case "claude-3-5-sonnet-20241022":
@@ -105,6 +106,7 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
 						// Then check for models that support prompt caching
 						switch (modelId) {
 							case "claude-sonnet-4-20250514":
+							case "claude-opus-4-1-20250805":
 							case "claude-opus-4-20250514":
 							case "claude-3-7-sonnet-20250219":
 							case "claude-3-5-sonnet-20241022":

src/api/providers/fetchers/__tests__/openrouter.spec.ts

@@ -32,6 +32,7 @@ describe("OpenRouter API", () => {
 				"google/gemini-2.5-pro-preview", // Excluded due to lag issue (#4487)
 				"google/gemini-2.5-flash", // OpenRouter doesn't report this as supporting prompt caching
 				"google/gemini-2.5-flash-lite-preview-06-17", // OpenRouter doesn't report this as supporting prompt caching
+				"anthropic/claude-opus-4.1", // Not yet available in OpenRouter API
 			])
 
 			const ourCachingModels = Array.from(OPEN_ROUTER_PROMPT_CACHING_MODELS).filter(
@@ -48,12 +49,20 @@ describe("OpenRouter API", () => {
 
 			expect(ourCachingModels.sort()).toEqual(expectedCachingModels)
 
+			const excludedComputerUseModels = new Set([
+				"anthropic/claude-opus-4.1", // Not yet available in OpenRouter API
+			])
+
+			const expectedComputerUseModels = Array.from(OPEN_ROUTER_COMPUTER_USE_MODELS)
+				.filter((id) => !excludedComputerUseModels.has(id))
+				.sort()
+
 			expect(
 				Object.entries(models)
 					.filter(([_, model]) => model.supportsComputerUse)
 					.map(([id, _]) => id)
 					.sort(),
-			).toEqual(Array.from(OPEN_ROUTER_COMPUTER_USE_MODELS).sort())
+			).toEqual(expectedComputerUseModels)
 
 			expect(
 				Object.entries(models)
@@ -67,6 +76,7 @@ describe("OpenRouter API", () => {
 				"anthropic/claude-3.7-sonnet:beta",
 				"anthropic/claude-3.7-sonnet:thinking",
 				"anthropic/claude-opus-4",
+				// "anthropic/claude-opus-4.1", // Not yet available in OpenRouter API
 				"anthropic/claude-sonnet-4",
 				"arliai/qwq-32b-arliai-rpr-v1:free",
 				"cognitivecomputations/dolphin3.0-r1-mistral-24b:free",
@@ -122,6 +132,7 @@ describe("OpenRouter API", () => {
 				"google/gemini-2.5-flash",
 				"google/gemini-2.5-flash-lite-preview-06-17",
 				"google/gemini-2.5-pro",
+				"anthropic/claude-opus-4.1", // Not yet available in OpenRouter API
 			])
 
 			const expectedReasoningBudgetModels = Array.from(OPEN_ROUTER_REASONING_BUDGET_MODELS)

src/api/providers/fetchers/openrouter.ts

@@ -232,6 +232,11 @@ export const parseOpenRouterModel = ({
 		modelInfo.maxTokens = anthropicModels["claude-3-7-sonnet-20250219:thinking"].maxTokens
 	}
 
+	// Set claude-opus-4.1 model to use the correct configuration
+	if (id === "anthropic/claude-opus-4.1") {
+		modelInfo.maxTokens = anthropicModels["claude-opus-4-1-20250805"].maxTokens
+	}
+
 	// Set horizon-alpha model to 32k max tokens
 	if (id === "openrouter/horizon-alpha") {
 		modelInfo.maxTokens = 32768