feat: add AWS Bedrock service tier support

- Add awsBedrockServiceTier field to provider settings schema
- Add tier-specific pricing for Claude models (FLEX ~20% discount, PRIORITY ~20% premium)
- Update Bedrock provider to include service_tier in API requests
- Add service tier selector UI in Bedrock settings
- Apply tier-specific pricing in cost calculations

Implements #9874

packages/types/src/provider-settings.ts

@@ -236,6 +236,8 @@ const bedrockSchema = apiModelIdProviderModelSchema.extend({
 	awsBedrockEndpointEnabled: z.boolean().optional(),
 	awsBedrockEndpoint: z.string().optional(),
 	awsBedrock1MContext: z.boolean().optional(), // Enable 'context-1m-2025-08-07' beta for 1M context window.
+	// AWS Bedrock service tier for models that support it (STANDARD, FLEX, PRIORITY)
+	awsBedrockServiceTier: serviceTierSchema.optional(),
 })
 
 const vertexSchema = apiModelIdProviderModelSchema.extend({

packages/types/src/providers/bedrock.ts

@@ -27,6 +27,25 @@ export const bedrockModels = {
 		minTokensPerCachePoint: 1024,
 		maxCachePoints: 4,
 		cachableFields: ["system", "messages", "tools"],
+		// Service tier pricing (FLEX ~20% discount, PRIORITY ~20% premium)
+		tiers: [
+			{
+				name: "flex" as const,
+				contextWindow: 200_000,
+				inputPrice: 2.4, // 20% discount
+				outputPrice: 12.0, // 20% discount
+				cacheWritesPrice: 3.0, // 20% discount
+				cacheReadsPrice: 0.24, // 20% discount
+			},
+			{
+				name: "priority" as const,
+				contextWindow: 200_000,
+				inputPrice: 3.6, // 20% premium
+				outputPrice: 18.0, // 20% premium
+				cacheWritesPrice: 4.5, // 20% premium
+				cacheReadsPrice: 0.36, // 20% premium
+			},
+		],
 	},
 	"amazon.nova-pro-v1:0": {
 		maxTokens: 5000,
@@ -184,6 +203,25 @@ export const bedrockModels = {
 		minTokensPerCachePoint: 2048,
 		maxCachePoints: 4,
 		cachableFields: ["system", "messages", "tools"],
+		// Service tier pricing (FLEX ~20% discount, PRIORITY ~20% premium)
+		tiers: [
+			{
+				name: "flex" as const,
+				contextWindow: 200_000,
+				inputPrice: 0.64, // 20% discount
+				outputPrice: 3.2, // 20% discount
+				cacheWritesPrice: 0.8, // 20% discount
+				cacheReadsPrice: 0.064, // 20% discount
+			},
+			{
+				name: "priority" as const,
+				contextWindow: 200_000,
+				inputPrice: 0.96, // 20% premium
+				outputPrice: 4.8, // 20% premium
+				cacheWritesPrice: 1.2, // 20% premium
+				cacheReadsPrice: 0.096, // 20% premium
+			},
+		],
 	},
 	"anthropic.claude-haiku-4-5-20251001-v1:0": {
 		maxTokens: 8192,
@@ -235,6 +273,21 @@ export const bedrockModels = {
 		supportsNativeTools: true,
 		inputPrice: 0.25,
 		outputPrice: 1.25,
+		// Service tier pricing (FLEX ~20% discount, PRIORITY ~20% premium)
+		tiers: [
+			{
+				name: "flex" as const,
+				contextWindow: 200_000,
+				inputPrice: 0.2, // 20% discount
+				outputPrice: 1.0, // 20% discount
+			},
+			{
+				name: "priority" as const,
+				contextWindow: 200_000,
+				inputPrice: 0.3, // 20% premium
+				outputPrice: 1.5, // 20% premium
+			},
+		],
 	},
 	"anthropic.claude-2-1-v1:0": {
 		maxTokens: 4096,

src/api/providers/bedrock.ts

@@ -53,13 +53,14 @@ interface BedrockInferenceConfig {
 }
 
 // Define interface for Bedrock additional model request fields
-// This includes thinking configuration, 1M context beta, and other model-specific parameters
+// This includes thinking configuration, 1M context beta, service tier, and other model-specific parameters
 interface BedrockAdditionalModelFields {
 	thinking?: {
 		type: "enabled"
 		budget_tokens: number
 	}
 	anthropic_beta?: string[]
+	service_tier?: "STANDARD" | "FLEX" | "PRIORITY"
 	[key: string]: any // Add index signature to be compatible with DocumentType
 }
 
@@ -433,6 +434,28 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 			additionalModelRequestFields.anthropic_beta = anthropicBetas
 		}
 
+		// Add service tier if specified and model supports it
+		if (this.options.awsBedrockServiceTier && modelConfig.info.tiers && modelConfig.info.tiers.length > 0) {
+			if (!additionalModelRequestFields) {
+				additionalModelRequestFields = {} as BedrockAdditionalModelFields
+			}
+			// Convert from lowercase to uppercase for API
+			const tierMap: Record<string, "STANDARD" | "FLEX" | "PRIORITY"> = {
+				default: "STANDARD",
+				flex: "FLEX",
+				priority: "PRIORITY",
+			}
+			const mappedTier = tierMap[this.options.awsBedrockServiceTier as string]
+			if (mappedTier) {
+				additionalModelRequestFields.service_tier = mappedTier
+				logger.info("Service tier specified for Bedrock request", {
+					ctx: "bedrock",
+					modelId: modelConfig.id,
+					serviceTier: mappedTier,
+				})
+			}
+		}
+
 		// Build tool configuration if native tools are enabled
 		let toolConfig: ToolConfiguration | undefined
 		if (useNativeTools && metadata?.tools) {
@@ -1027,15 +1050,18 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 		reasoningBudget?: number
 	} {
 		if (this.costModelConfig?.id?.trim().length > 0) {
+			// Apply service tier pricing if specified
+			const tierAdjustedInfo = this.applyServiceTierPricing(this.costModelConfig.info)
+
 			// Get model params for cost model config
 			const params = getModelParams({
 				format: "anthropic",
 				modelId: this.costModelConfig.id,
-				model: this.costModelConfig.info,
+				model: tierAdjustedInfo,
 				settings: this.options,
 				defaultTemperature: BEDROCK_DEFAULT_TEMPERATURE,
 			})
-			return { ...this.costModelConfig, ...params }
+			return { ...this.costModelConfig, info: tierAdjustedInfo, ...params }
 		}
 
 		let modelConfig = undefined
@@ -1080,17 +1106,20 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 			}
 		}
 
+		// Apply service tier pricing if specified
+		const tierAdjustedInfo = this.applyServiceTierPricing(modelConfig.info)
+
 		// Get model params including reasoning configuration
 		const params = getModelParams({
 			format: "anthropic",
 			modelId: modelConfig.id,
-			model: modelConfig.info,
+			model: tierAdjustedInfo,
 			settings: this.options,
 			defaultTemperature: BEDROCK_DEFAULT_TEMPERATURE,
 		})
 
 		// Don't override maxTokens/contextWindow here; handled in getModelById (and includes user overrides)
-		return { ...modelConfig, ...params } as {
+		return { ...modelConfig, info: tierAdjustedInfo, ...params } as {
 			id: BedrockModelId | string
 			info: ModelInfo
 			maxTokens?: number
@@ -1230,6 +1259,33 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 		return false
 	}
 
+	/************************************************************************************
+	 *
+	 *     SERVICE TIER PRICING
+	 *
+	 *************************************************************************************/
+
+	/**
+	 * Returns a shallow-cloned ModelInfo with pricing overridden for the given tier, if available.
+	 * If no tier or no overrides exist, the original ModelInfo is returned.
+	 */
+	private applyServiceTierPricing(info: ModelInfo): ModelInfo {
+		const tier = this.options.awsBedrockServiceTier
+		if (!tier || tier === "default") return info
+
+		// Find the tier with matching name in the tiers array
+		const tierInfo = info.tiers?.find((t) => t.name === tier)
+		if (!tierInfo) return info
+
+		return {
+			...info,
+			inputPrice: tierInfo.inputPrice ?? info.inputPrice,
+			outputPrice: tierInfo.outputPrice ?? info.outputPrice,
+			cacheReadsPrice: tierInfo.cacheReadsPrice ?? info.cacheReadsPrice,
+			cacheWritesPrice: tierInfo.cacheWritesPrice ?? info.cacheWritesPrice,
+		}
+	}
+
 	/************************************************************************************
 	 *
 	 *     ERROR HANDLING

webview-ui/src/components/settings/providers/Bedrock.tsx

@@ -35,6 +35,9 @@ export const Bedrock = ({ apiConfiguration, setApiConfigurationField, selectedMo
 		!!apiConfiguration?.apiModelId &&
 		BEDROCK_GLOBAL_INFERENCE_MODEL_IDS.includes(apiConfiguration.apiModelId as any)
 
+	// Check if the selected model supports service tiers
+	const supportsServiceTiers = !!(selectedModelInfo?.tiers && selectedModelInfo.tiers.length > 0)
+
 	// Update the endpoint enabled state when the configuration changes
 	useEffect(() => {
 		setAwsEndpointSelected(!!apiConfiguration?.awsBedrockEndpointEnabled)
@@ -150,6 +153,26 @@ export const Bedrock = ({ apiConfiguration, setApiConfigurationField, selectedMo
 					</SelectContent>
 				</Select>
 			</div>
+			{supportsServiceTiers && (
+				<div>
+					<label className="block font-medium mb-1">Service Tier</label>
+					<Select
+						value={apiConfiguration?.awsBedrockServiceTier || "default"}
+						onValueChange={(value) => setApiConfigurationField("awsBedrockServiceTier", value)}>
+						<SelectTrigger className="w-full">
+							<SelectValue placeholder="Select service tier" />
+						</SelectTrigger>
+						<SelectContent>
+							<SelectItem value="default">Standard (Default)</SelectItem>
+							<SelectItem value="flex">Flex (Lower cost, higher latency)</SelectItem>
+							<SelectItem value="priority">Priority (Lower latency, higher cost)</SelectItem>
+						</SelectContent>
+					</Select>
+					<div className="text-sm text-vscode-descriptionForeground mt-1">
+						Choose the service tier based on your cost and latency requirements
+					</div>
+				</div>
+			)}
 			{supportsGlobalInference && (
 				<Checkbox
 					checked={apiConfiguration?.awsUseGlobalInference || false}