diff --git a/backend/internal/pkg/apicompat/types.go b/backend/internal/pkg/apicompat/types.go
index cfc4b0aa..f8c6b75f 100644
--- a/backend/internal/pkg/apicompat/types.go
+++ b/backend/internal/pkg/apicompat/types.go
@@ -82,10 +82,18 @@ type AnthropicImageSource struct {
 
 // AnthropicTool describes a tool available to the model.
 type AnthropicTool struct {
-	Type        string          `json:"type,omitempty"` // e.g. "web_search_20250305" for server tools
-	Name        string          `json:"name"`
-	Description string          `json:"description,omitempty"`
-	InputSchema json.RawMessage `json:"input_schema"` // JSON Schema object
+	Type         string                 `json:"type,omitempty"` // e.g. "web_search_20250305" for server tools
+	Name         string                 `json:"name"`
+	Description  string                 `json:"description,omitempty"`
+	InputSchema  json.RawMessage        `json:"input_schema"` // JSON Schema object
+	CacheControl *AnthropicCacheControl `json:"cache_control,omitempty"`
+}
+
+// AnthropicCacheControl 对应 Anthropic API 的 cache_control 字段。
+// ttl 默认由调用方决定；本项目策略见 claude.DefaultCacheControlTTL。
+type AnthropicCacheControl struct {
+	Type string `json:"type"`          // "ephemeral"
+	TTL  string `json:"ttl,omitempty"` // "5m" / "1h" / 省略=默认 5m（由 Anthropic 判定）
 }
 
 // AnthropicResponse is the non-streaming response from POST /v1/messages.
diff --git a/backend/internal/pkg/claude/constants.go b/backend/internal/pkg/claude/constants.go
index 3c92c3e3..594d91ad 100644
--- a/backend/internal/pkg/claude/constants.go
+++ b/backend/internal/pkg/claude/constants.go
@@ -57,6 +57,11 @@ const APIKeyBetaHeader = BetaClaudeCode + "," + BetaInterleavedThinking + "," +
 // APIKeyHaikuBetaHeader Haiku 模型在 API-key 账号下使用的 anthropic-beta header（不包含 oauth / claude-code）
 const APIKeyHaikuBetaHeader = BetaInterleavedThinking
 
+// DefaultCacheControlTTL 是网关代理为自己生成的 cache_control 块默认使用的 ttl。
+// 真实 Claude Code CLI 当前使用 "1h"，但本仓策略是"客户端透传 ttl 优先；
+// 客户端缺省时统一使用 5m"，这样既不浪费 1h 缓存额度，也保留客户端自定义能力。
+const DefaultCacheControlTTL = "5m"
+
 // FullClaudeCodeMimicryBetas 返回最"像"真实 Claude Code CLI 的完整 beta 列表，
 // 用于 OAuth 账号伪装成 Claude Code 时使用。
 // 顺序与真实 CLI 抓包一致。
diff --git a/backend/internal/service/gateway_service.go b/backend/internal/service/gateway_service.go
index 4315808c..5ca5de0c 100644
--- a/backend/internal/service/gateway_service.go
+++ b/backend/internal/service/gateway_service.go
@@ -850,6 +850,7 @@ func (s *GatewayService) hashContent(content string) string {
 
 type anthropicCacheControlPayload struct {
 	Type string `json:"type"`
+	TTL  string `json:"ttl,omitempty"`
 }
 
 type anthropicSystemTextBlockPayload struct {
@@ -898,7 +899,10 @@ func marshalAnthropicSystemTextBlock(text string, includeCacheControl bool) ([]b
 		Text: text,
 	}
 	if includeCacheControl {
-		block.CacheControl = &anthropicCacheControlPayload{Type: "ephemeral"}
+		block.CacheControl = &anthropicCacheControlPayload{
+			Type: "ephemeral",
+			TTL:  claude.DefaultCacheControlTTL,
+		}
 	}
 	return json.Marshal(block)
 }
@@ -3856,7 +3860,7 @@ func rewriteSystemForNonClaudeCode(body []byte, system any) []byte {
 		{
 			"type":          "text",
 			"text":          claudeCodeSystemPrompt,
-			"cache_control": map[string]string{"type": "ephemeral"},
+			"cache_control": map[string]string{"type": "ephemeral", "ttl": claude.DefaultCacheControlTTL},
 		},
 	}
 	out, ok := setJSONValueBytes(body, "system", claudeCodeSystemBlock)