Add Fable 5 support across Anthropic providers (#555)

* Add Fable 5 support to Anthropic providers

* fix(providers): address PR #555 review feedback for Fable 5

---------

Co-authored-by: Elliott de Launay <edelauna@gmail.com>

Author: taltas

packages/types/src/providers/anthropic.ts

@@ -126,6 +126,23 @@ export const anthropicModels = {
 		supportsReasoningBinary: true,
 		supportsTemperature: false,
 	},
+	"claude-fable-5": {
+		maxTokens: 128_000, // Overridden to 8k if `enableReasoningEffort` is false.
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 10.0, // $10 per million input tokens
+		outputPrice: 50.0, // $50 per million output tokens
+		cacheWritesPrice: 12.5, // $12.50 per million tokens
+		cacheReadsPrice: 1.0, // $1.00 per million tokens
+		// Fable 5 uses the same adaptive-thinking / binary-toggle convention as
+		// Opus 4.7+ on the direct Anthropic provider path.
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"claude-opus-4-5-20251101": {
 		maxTokens: 32_000, // Overridden to 8k if `enableReasoningEffort` is false.
 		contextWindow: 200_000,

packages/types/src/providers/bedrock.ts

@@ -217,6 +217,24 @@ export const bedrockModels = {
 			},
 		],
 	},
+	"anthropic.claude-fable-5": {
+		maxTokens: 8192,
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		inputPrice: 10.0,
+		outputPrice: 50.0,
+		cacheWritesPrice: 12.5,
+		cacheReadsPrice: 1.0,
+		minTokensPerCachePoint: 1024,
+		maxCachePoints: 4,
+		cachableFields: ["system", "messages", "tools"],
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"anthropic.claude-opus-4-5-20251101-v1:0": {
 		maxTokens: 8192,
 		contextWindow: 200_000,
@@ -588,6 +606,7 @@ export const BEDROCK_1M_CONTEXT_MODEL_IDS = [
 // - Claude Opus 4.5
 // - Claude Opus 4.6
 // - Claude Opus 4.7
+// - Claude Fable 5 (cross-region inference only — can only be used through an inference profile)
 export const BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
 	"anthropic.claude-sonnet-4-20250514-v1:0",
 	"anthropic.claude-sonnet-4-5-20250929-v1:0",
@@ -597,6 +616,7 @@ export const BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
 	"anthropic.claude-opus-4-6-v1",
 	"anthropic.claude-opus-4-7",
 	"anthropic.claude-opus-4-8",
+	"anthropic.claude-fable-5",
 ] as const
 
 // Amazon Bedrock Service Tier types

packages/types/src/providers/openrouter.ts

@@ -43,6 +43,7 @@ export const OPEN_ROUTER_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-haiku-4.5",
 	"google/gemini-2.5-flash-preview",
 	"google/gemini-2.5-flash-preview:thinking",
@@ -74,6 +75,7 @@ export const OPEN_ROUTER_REASONING_BUDGET_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.5",
 	"anthropic/claude-sonnet-4.6",

packages/types/src/providers/vercel-ai-gateway.ts

@@ -13,6 +13,7 @@ export const VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.6",
 	"openai/gpt-4.1",
@@ -55,6 +56,7 @@ export const VERCEL_AI_GATEWAY_VISION_AND_TOOLS_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.6",
 	"google/gemini-1.5-flash",

packages/types/src/providers/vertex.ts

@@ -434,6 +434,21 @@ export const vertexModels = {
 			},
 		],
 	},
+	"claude-fable-5": {
+		maxTokens: 8192,
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 10.0,
+		outputPrice: 50.0,
+		cacheWritesPrice: 12.5,
+		cacheReadsPrice: 1.0,
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"claude-opus-4-5@20251101": {
 		maxTokens: 8192,
 		contextWindow: 200_000,

src/api/providers/__tests__/anthropic-vertex.spec.ts

@@ -945,6 +945,23 @@ describe("VertexHandler", () => {
 			expect(model.betas).toContain("context-1m-2025-08-07")
 		})
 
+		it("should return Claude Fable 5 model info", () => {
+			const handler = new AnthropicVertexHandler({
+				apiModelId: "claude-fable-5",
+				vertexProjectId: "test-project",
+				vertexRegion: "us-central1",
+			})
+
+			const model = handler.getModel()
+			expect(model.id).toBe("claude-fable-5")
+			expect(model.info.maxTokens).toBe(8192)
+			expect(model.info.contextWindow).toBe(1_000_000)
+			expect(model.info.supportsReasoningBinary).toBe(true)
+			expect(model.info.supportsReasoningBudget).toBe(true)
+			expect(model.info.supportsPromptCache).toBe(true)
+			expect(model.info.supportsTemperature).toBe(false)
+		})
+
 		it("should not enable 1M context when flag is disabled", () => {
 			const handler = new AnthropicVertexHandler({
 				apiModelId: VERTEX_1M_CONTEXT_MODEL_IDS[0],
@@ -1192,6 +1209,35 @@ describe("VertexHandler", () => {
 			expect(request.thinking).not.toHaveProperty("budget_tokens")
 			expect(request.temperature).toBeUndefined()
 		})
+
+		it("should use adaptive thinking for Claude Fable 5", async () => {
+			const fableHandler = new AnthropicVertexHandler({
+				apiModelId: "claude-fable-5",
+				vertexProjectId: "test-project",
+				vertexRegion: "us-central1",
+				enableReasoningEffort: true,
+			})
+
+			const mockCreate = vitest.fn().mockImplementation(async () => ({
+				async *[Symbol.asyncIterator]() {
+					yield { type: "message_start", message: { usage: { input_tokens: 10, output_tokens: 5 } } }
+				},
+			}))
+			;(fableHandler["client"].messages as any).create = mockCreate
+
+			await fableHandler.createMessage("You are a helpful assistant", [{ role: "user", content: "Hello" }]).next()
+
+			expect(mockCreate).toHaveBeenCalledWith(
+				expect.objectContaining({
+					thinking: { type: "adaptive" },
+				}),
+				undefined,
+			)
+
+			const request = mockCreate.mock.calls[0][0]
+			expect(request.thinking).not.toHaveProperty("budget_tokens")
+			expect(request.temperature).toBeUndefined()
+		})
 	})
 
 	describe("native tool calling", () => {

src/api/providers/__tests__/anthropic.spec.ts

@@ -399,6 +399,33 @@ describe("AnthropicHandler", () => {
 			expect(requestBody?.thinking).toEqual({ type: "adaptive" })
 			expect(requestBody?.max_tokens).toBe(32768)
 		})
+
+		it("should use adaptive thinking for Claude Fable 5 when reasoning is enabled", async () => {
+			const fableHandler = new AnthropicHandler({
+				apiKey: "test-api-key",
+				apiModelId: "claude-fable-5",
+				enableReasoningEffort: true,
+				modelMaxTokens: 32768,
+			})
+
+			const stream = fableHandler.createMessage(systemPrompt, [
+				{
+					role: "user",
+					content: [{ type: "text" as const, text: "Hello" }],
+				},
+			])
+
+			for await (const _chunk of stream) {
+				// Consume stream
+			}
+
+			const requestBody = mockCreate.mock.calls[mockCreate.mock.calls.length - 1]?.[0]
+			const requestOptions = mockCreate.mock.calls[mockCreate.mock.calls.length - 1]?.[1]
+			expect(requestBody?.thinking).toEqual({ type: "adaptive" })
+			expect(requestBody?.temperature).toBeUndefined()
+			expect(requestBody?.max_tokens).toBe(32768)
+			expect(requestOptions?.headers?.["anthropic-beta"]).toContain("prompt-caching-2024-07-31")
+		})
 	})
 
 	describe("completePrompt", () => {
@@ -543,6 +570,23 @@ describe("AnthropicHandler", () => {
 			expect(model.reasoningBudget).toBeUndefined()
 		})
 
+		it("should handle Claude Fable 5 model correctly", () => {
+			const handler = new AnthropicHandler({
+				apiKey: "test-api-key",
+				apiModelId: "claude-fable-5",
+			})
+			const model = handler.getModel()
+			expect(model.id).toBe("claude-fable-5")
+			expect(model.info.maxTokens).toBe(128000)
+			expect(model.info.contextWindow).toBe(1000000)
+			expect(model.maxTokens).toBe(8192)
+			expect(model.info.supportsReasoningBinary).toBe(true)
+			expect(model.info.supportsReasoningBudget).toBe(true)
+			expect(model.info.supportsPromptCache).toBe(true)
+			expect(model.info.supportsTemperature).toBe(false)
+			expect(model.reasoningBudget).toBeUndefined()
+		})
+
 		it("should enable 1M context for Claude 4.5 Sonnet when beta flag is set", () => {
 			const handler = new AnthropicHandler({
 				apiKey: "test-api-key",

src/api/providers/__tests__/bedrock.spec.ts

@@ -691,6 +691,37 @@ describe("AwsBedrockHandler", () => {
 			expect(typeof model.info.supportsImages).toBe("boolean")
 			expect(typeof model.info.supportsPromptCache).toBe("boolean")
 		})
+
+		it("should return Claude Fable 5 model info", () => {
+			const handler = new AwsBedrockHandler({
+				apiModelId: "anthropic.claude-fable-5",
+				awsAccessKey: "test",
+				awsSecretKey: "test",
+				awsRegion: "us-east-1",
+			})
+
+			const model = handler.getModel()
+			expect(model.id).toBe("anthropic.claude-fable-5")
+			expect(model.info.contextWindow).toBe(1_000_000)
+			expect(model.info.supportsReasoningBinary).toBe(true)
+			expect(model.info.supportsReasoningBudget).toBe(true)
+			expect(model.info.supportsPromptCache).toBe(true)
+			expect(model.info.supportsTemperature).toBe(false)
+			expect(model.maxTokens).toBe(8192)
+		})
+
+		it("should apply global inference prefix for Claude Fable 5 when awsUseGlobalInference is true", () => {
+			const handler = new AwsBedrockHandler({
+				apiModelId: "anthropic.claude-fable-5",
+				awsAccessKey: "test",
+				awsSecretKey: "test",
+				awsRegion: "us-east-1",
+				awsUseGlobalInference: true,
+			})
+
+			const model = handler.getModel()
+			expect(model.id).toBe("global.anthropic.claude-fable-5")
+		})
 	})
 
 	describe("1M context beta feature", () => {
@@ -1524,13 +1555,15 @@ describe("AwsBedrockHandler", () => {
 			it("returns true for all adaptive-thinking model patterns (opus/sonnet 4.7 and 4.8)", () => {
 				expect(isAdaptiveThinkingModel("anthropic.claude-opus-4-7")).toBe(true)
 				expect(isAdaptiveThinkingModel("anthropic.claude-opus-4-8")).toBe(true)
+				expect(isAdaptiveThinkingModel("anthropic.claude-fable-5")).toBe(true)
 				// Future-proof Sonnet patterns — guarded even before a registry entry exists.
 				expect(isAdaptiveThinkingModel("anthropic.claude-sonnet-4-7")).toBe(true)
 				expect(isAdaptiveThinkingModel("anthropic.claude-sonnet-4-8")).toBe(true)
 			})
 
 			it("returns true when the id carries a cross-region or global prefix", () => {
 				expect(isAdaptiveThinkingModel("us.anthropic.claude-opus-4-8")).toBe(true)
+				expect(isAdaptiveThinkingModel("global.anthropic.claude-fable-5")).toBe(true)
 				expect(isAdaptiveThinkingModel("eu.anthropic.claude-sonnet-4-7")).toBe(true)
 				expect(isAdaptiveThinkingModel("global.anthropic.claude-opus-4-8")).toBe(true)
 			})

src/api/providers/__tests__/requesty.spec.ts

@@ -38,6 +38,20 @@ vitest.mock("../fetchers/modelCache", () => ({
 				cacheReadsPrice: 0.3,
 				description: "Claude 4 Sonnet",
 			},
+			"anthropic/claude-fable-5": {
+				maxTokens: 128000,
+				contextWindow: 1000000,
+				supportsImages: true,
+				supportsPromptCache: true,
+				supportsReasoningBudget: true,
+				supportsReasoningBinary: true,
+				supportsTemperature: false,
+				inputPrice: 10,
+				outputPrice: 50,
+				cacheWritesPrice: 12.5,
+				cacheReadsPrice: 1,
+				description: "Claude Fable 5",
+			},
 		})
 	}),
 }))
@@ -193,6 +207,39 @@ describe("RequestyHandler", () => {
 			)
 		})
 
+		it("uses adaptive thinking for Claude Fable 5 when reasoning is enabled", async () => {
+			const handler = new RequestyHandler({
+				requestyApiKey: "test-key",
+				requestyModelId: "anthropic/claude-fable-5",
+				enableReasoningEffort: true,
+				modelMaxTokens: 32768,
+			})
+
+			const mockStream = {
+				async *[Symbol.asyncIterator]() {
+					yield {
+						id: "test-id",
+						choices: [{ delta: {} }],
+						usage: { prompt_tokens: 10, completion_tokens: 20 },
+					}
+				},
+			}
+
+			mockCreate.mockResolvedValue(mockStream)
+
+			const generator = handler.createMessage("test system prompt", [{ role: "user" as const, content: "test" }])
+			await generator.next()
+
+			expect(mockCreate).toHaveBeenCalledWith(
+				expect.objectContaining({
+					model: "anthropic/claude-fable-5",
+					max_tokens: 32768,
+					thinking: { type: "adaptive" },
+					temperature: undefined,
+				}),
+			)
+		})
+
 		it("handles API errors", async () => {
 			const handler = new RequestyHandler(mockOptions)
 			const mockError = new Error("API Error")
@@ -367,6 +414,23 @@ describe("RequestyHandler", () => {
 			})
 		})
 
+		it("omits temperature for Claude Fable 5 in completePrompt", async () => {
+			const handler = new RequestyHandler({
+				requestyApiKey: "test-key",
+				requestyModelId: "anthropic/claude-fable-5",
+			})
+			mockCreate.mockResolvedValue({ choices: [{ message: { content: "test completion" } }] })
+
+			await handler.completePrompt("test prompt")
+
+			expect(mockCreate).toHaveBeenCalledWith({
+				model: "anthropic/claude-fable-5",
+				max_tokens: 8192,
+				messages: [{ role: "system", content: "test prompt" }],
+				temperature: undefined,
+			})
+		})
+
 		it("handles API errors", async () => {
 			const handler = new RequestyHandler(mockOptions)
 			const mockError = new Error("API Error")