diff --git a/packages/types/src/providers/vercel-ai-gateway.ts b/packages/types/src/providers/vercel-ai-gateway.ts
index 837baf7c52..bded0b530d 100644
--- a/packages/types/src/providers/vercel-ai-gateway.ts
+++ b/packages/types/src/providers/vercel-ai-gateway.ts
@@ -3,6 +3,29 @@ import type { ModelInfo } from "../model.js"
 // https://ai-gateway.vercel.sh/v1/
 export const vercelAiGatewayDefaultModelId = "anthropic/claude-sonnet-4"
 
+export const VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS = new Set([
+	"anthropic/claude-3-haiku",
+	"anthropic/claude-3-opus",
+	"anthropic/claude-3.5-haiku",
+	"anthropic/claude-3.5-sonnet",
+	"anthropic/claude-3.7-sonnet",
+	"anthropic/claude-opus-4",
+	"anthropic/claude-opus-4.1",
+	"anthropic/claude-sonnet-4",
+	"openai/gpt-4.1",
+	"openai/gpt-4.1-mini",
+	"openai/gpt-4.1-nano",
+	"openai/gpt-4o",
+	"openai/gpt-4o-mini",
+	"openai/gpt-5",
+	"openai/gpt-5-mini",
+	"openai/gpt-5-nano",
+	"openai/o1",
+	"openai/o3",
+	"openai/o3-mini",
+	"openai/o4-mini",
+])
+
 export const vercelAiGatewayDefaultModelInfo: ModelInfo = {
 	maxTokens: 64000,
 	contextWindow: 128000,
diff --git a/src/api/providers/vercel-ai-gateway.ts b/src/api/providers/vercel-ai-gateway.ts
index 87fb7bab9c..0b14d43c63 100644
--- a/src/api/providers/vercel-ai-gateway.ts
+++ b/src/api/providers/vercel-ai-gateway.ts
@@ -5,13 +5,14 @@ import {
 	vercelAiGatewayDefaultModelId,
 	vercelAiGatewayDefaultModelInfo,
 	VERCEL_AI_GATEWAY_DEFAULT_TEMPERATURE,
+	VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS,
 } from "@roo-code/types"
 
 import { ApiHandlerOptions } from "../../shared/api"
 
 import { ApiStream } from "../transform/stream"
 import { convertToOpenAiMessages } from "../transform/openai-format"
-import { addCacheBreakpoints } from "../transform/caching/anthropic"
+import { addCacheBreakpoints } from "../transform/caching/vercel-ai-gateway"
 
 import type { SingleCompletionHandler, ApiHandlerCreateMessageMetadata } from "../index"
 import { RouterProvider } from "./router-provider"
@@ -49,9 +50,9 @@ export class VercelAiGatewayHandler extends RouterProvider implements SingleComp
 			...convertToOpenAiMessages(messages),
 		]
 
-		if (modelId.startsWith("anthropic/claude-3")) {
+		if (VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS.has(modelId) && info.supportsPromptCache) {
 			addCacheBreakpoints(systemPrompt, openAiMessages)
-		} //TODO: add cache breakpoints for other models
+		}
 
 		const body: OpenAI.Chat.ChatCompletionCreateParams = {
 			model: modelId,
diff --git a/src/api/transform/caching/vercel-ai-gateway.ts b/src/api/transform/caching/vercel-ai-gateway.ts
new file mode 100644
index 0000000000..82eff0cd7b
--- /dev/null
+++ b/src/api/transform/caching/vercel-ai-gateway.ts
@@ -0,0 +1,30 @@
+import OpenAI from "openai"
+
+export function addCacheBreakpoints(systemPrompt: string, messages: OpenAI.Chat.ChatCompletionMessageParam[]) {
+	// Apply cache_control to system message at the message level
+	messages[0] = {
+		role: "system",
+		content: systemPrompt,
+		// @ts-ignore-next-line
+		cache_control: { type: "ephemeral" },
+	}
+
+	// Add cache_control to the last two user messages for conversation context caching
+	const lastTwoUserMessages = messages.filter((msg) => msg.role === "user").slice(-2)
+
+	lastTwoUserMessages.forEach((msg) => {
+		if (typeof msg.content === "string" && msg.content.length > 0) {
+			msg.content = [{ type: "text", text: msg.content }]
+		}
+
+		if (Array.isArray(msg.content)) {
+			// Find the last text part in the message content
+			let lastTextPart = msg.content.filter((part) => part.type === "text").pop()
+
+			if (lastTextPart && lastTextPart.text && lastTextPart.text.length > 0) {
+				// @ts-ignore-next-line
+				lastTextPart["cache_control"] = { type: "ephemeral" }
+			}
+		}
+	})
+}
diff --git a/webview-ui/src/i18n/locales/de/settings.json b/webview-ui/src/i18n/locales/de/settings.json
index 71006a9d4c..b9465d6c59 100644
--- a/webview-ui/src/i18n/locales/de/settings.json
+++ b/webview-ui/src/i18n/locales/de/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Stellen Sie sicher, dass die Region in der ARN mit Ihrer oben ausgewählten AWS-Region übereinstimmt.",
 		"openRouterApiKey": "OpenRouter API-Schlüssel",
 		"getOpenRouterApiKey": "OpenRouter API-Schlüssel erhalten",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway API-Schlüssel",
 		"doubaoApiKey": "Doubao API-Schlüssel",
 		"getDoubaoApiKey": "Doubao API-Schlüssel erhalten",
 		"apiKeyStorageNotice": "API-Schlüssel werden sicher im VSCode Secret Storage gespeichert",
diff --git a/webview-ui/src/i18n/locales/en/settings.json b/webview-ui/src/i18n/locales/en/settings.json
index 6d761e85ff..85bf310910 100644
--- a/webview-ui/src/i18n/locales/en/settings.json
+++ b/webview-ui/src/i18n/locales/en/settings.json
@@ -232,6 +232,7 @@
 		"awsCustomArnDesc": "Make sure the region in the ARN matches your selected AWS Region above.",
 		"openRouterApiKey": "OpenRouter API Key",
 		"getOpenRouterApiKey": "Get OpenRouter API Key",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway API Key",
 		"apiKeyStorageNotice": "API keys are stored securely in VSCode's Secret Storage",
 		"glamaApiKey": "Glama API Key",
 		"getGlamaApiKey": "Get Glama API Key",
diff --git a/webview-ui/src/i18n/locales/es/settings.json b/webview-ui/src/i18n/locales/es/settings.json
index a3dbfa410c..6eb3b5c3eb 100644
--- a/webview-ui/src/i18n/locales/es/settings.json
+++ b/webview-ui/src/i18n/locales/es/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Asegúrese de que la región en el ARN coincida con la región de AWS seleccionada anteriormente.",
 		"openRouterApiKey": "Clave API de OpenRouter",
 		"getOpenRouterApiKey": "Obtener clave API de OpenRouter",
+		"vercelAiGatewayApiKey": "Clave API de Vercel AI Gateway",
 		"apiKeyStorageNotice": "Las claves API se almacenan de forma segura en el Almacenamiento Secreto de VSCode",
 		"glamaApiKey": "Clave API de Glama",
 		"getGlamaApiKey": "Obtener clave API de Glama",
diff --git a/webview-ui/src/i18n/locales/fr/settings.json b/webview-ui/src/i18n/locales/fr/settings.json
index a2c2d0ca06..50124518d1 100644
--- a/webview-ui/src/i18n/locales/fr/settings.json
+++ b/webview-ui/src/i18n/locales/fr/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Assurez-vous que la région dans l'ARN correspond à la région AWS sélectionnée ci-dessus.",
 		"openRouterApiKey": "Clé API OpenRouter",
 		"getOpenRouterApiKey": "Obtenir la clé API OpenRouter",
+		"vercelAiGatewayApiKey": "Clé API Vercel AI Gateway",
 		"apiKeyStorageNotice": "Les clés API sont stockées en toute sécurité dans le stockage sécurisé de VSCode",
 		"glamaApiKey": "Clé API Glama",
 		"getGlamaApiKey": "Obtenir la clé API Glama",
diff --git a/webview-ui/src/i18n/locales/it/settings.json b/webview-ui/src/i18n/locales/it/settings.json
index 0cc2a59019..66ec621813 100644
--- a/webview-ui/src/i18n/locales/it/settings.json
+++ b/webview-ui/src/i18n/locales/it/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Assicurati che la regione nell'ARN corrisponda alla regione AWS selezionata sopra.",
 		"openRouterApiKey": "Chiave API OpenRouter",
 		"getOpenRouterApiKey": "Ottieni chiave API OpenRouter",
+		"vercelAiGatewayApiKey": "Chiave API Vercel AI Gateway",
 		"apiKeyStorageNotice": "Le chiavi API sono memorizzate in modo sicuro nell'Archivio Segreto di VSCode",
 		"glamaApiKey": "Chiave API Glama",
 		"getGlamaApiKey": "Ottieni chiave API Glama",
diff --git a/webview-ui/src/i18n/locales/ja/settings.json b/webview-ui/src/i18n/locales/ja/settings.json
index 27b51854dd..4e9b2848e2 100644
--- a/webview-ui/src/i18n/locales/ja/settings.json
+++ b/webview-ui/src/i18n/locales/ja/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "ARN内のリージョンが上で選択したAWSリージョンと一致していることを確認してください。",
 		"openRouterApiKey": "OpenRouter APIキー",
 		"getOpenRouterApiKey": "OpenRouter APIキーを取得",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway APIキー",
 		"apiKeyStorageNotice": "APIキーはVSCodeのシークレットストレージに安全に保存されます",
 		"glamaApiKey": "Glama APIキー",
 		"getGlamaApiKey": "Glama APIキーを取得",
diff --git a/webview-ui/src/i18n/locales/ko/settings.json b/webview-ui/src/i18n/locales/ko/settings.json
index e6125f0ca8..2837b2dec3 100644
--- a/webview-ui/src/i18n/locales/ko/settings.json
+++ b/webview-ui/src/i18n/locales/ko/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "ARN의 리전이 위에서 선택한 AWS 리전과 일치하는지 확인하세요.",
 		"openRouterApiKey": "OpenRouter API 키",
 		"getOpenRouterApiKey": "OpenRouter API 키 받기",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway API 키",
 		"apiKeyStorageNotice": "API 키는 VSCode의 보안 저장소에 안전하게 저장됩니다",
 		"glamaApiKey": "Glama API 키",
 		"getGlamaApiKey": "Glama API 키 받기",
diff --git a/webview-ui/src/i18n/locales/pt-BR/settings.json b/webview-ui/src/i18n/locales/pt-BR/settings.json
index 7039497b94..197c7af922 100644
--- a/webview-ui/src/i18n/locales/pt-BR/settings.json
+++ b/webview-ui/src/i18n/locales/pt-BR/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Certifique-se de que a região no ARN corresponde à região AWS selecionada acima.",
 		"openRouterApiKey": "Chave de API OpenRouter",
 		"getOpenRouterApiKey": "Obter chave de API OpenRouter",
+		"vercelAiGatewayApiKey": "Chave API do Vercel AI Gateway",
 		"apiKeyStorageNotice": "As chaves de API são armazenadas com segurança no Armazenamento Secreto do VSCode",
 		"glamaApiKey": "Chave de API Glama",
 		"getGlamaApiKey": "Obter chave de API Glama",
diff --git a/webview-ui/src/i18n/locales/ru/settings.json b/webview-ui/src/i18n/locales/ru/settings.json
index 05d73cd46f..a88dcfbc69 100644
--- a/webview-ui/src/i18n/locales/ru/settings.json
+++ b/webview-ui/src/i18n/locales/ru/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "Убедитесь, что регион в ARN совпадает с выбранным выше регионом AWS.",
 		"openRouterApiKey": "OpenRouter API-ключ",
 		"getOpenRouterApiKey": "Получить OpenRouter API-ключ",
+		"vercelAiGatewayApiKey": "Ключ API Vercel AI Gateway",
 		"apiKeyStorageNotice": "API-ключи хранятся безопасно в Secret Storage VSCode",
 		"glamaApiKey": "Glama API-ключ",
 		"getGlamaApiKey": "Получить Glama API-ключ",
diff --git a/webview-ui/src/i18n/locales/zh-CN/settings.json b/webview-ui/src/i18n/locales/zh-CN/settings.json
index a7d3077684..94b3db1885 100644
--- a/webview-ui/src/i18n/locales/zh-CN/settings.json
+++ b/webview-ui/src/i18n/locales/zh-CN/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "请确保ARN中的区域与上方选择的AWS区域一致。",
 		"openRouterApiKey": "OpenRouter API 密钥",
 		"getOpenRouterApiKey": "获取 OpenRouter API 密钥",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway API 密钥",
 		"apiKeyStorageNotice": "API 密钥安全存储在 VSCode 的密钥存储中",
 		"glamaApiKey": "Glama API 密钥",
 		"getGlamaApiKey": "获取 Glama API 密钥",
diff --git a/webview-ui/src/i18n/locales/zh-TW/settings.json b/webview-ui/src/i18n/locales/zh-TW/settings.json
index d8b71601dc..31359291ce 100644
--- a/webview-ui/src/i18n/locales/zh-TW/settings.json
+++ b/webview-ui/src/i18n/locales/zh-TW/settings.json
@@ -233,6 +233,7 @@
 		"awsCustomArnDesc": "確保 ARN 中的區域與您上面選擇的 AWS 區域相符。",
 		"openRouterApiKey": "OpenRouter API 金鑰",
 		"getOpenRouterApiKey": "取得 OpenRouter API 金鑰",
+		"vercelAiGatewayApiKey": "Vercel AI Gateway API 金鑰",
 		"apiKeyStorageNotice": "API 金鑰安全儲存於 VSCode 金鑰儲存中",
 		"glamaApiKey": "Glama API 金鑰",
 		"getGlamaApiKey": "取得 Glama API 金鑰",