diff --git a/plugins/wasm-go/extensions/ai-cache/README.md b/plugins/wasm-go/extensions/ai-cache/README.md
index 97728f517..1de252f12 100644
--- a/plugins/wasm-go/extensions/ai-cache/README.md
+++ b/plugins/wasm-go/extensions/ai-cache/README.md
@@ -9,6 +9,11 @@ description: AI 缓存插件配置参考
 
 LLM 结果缓存插件，默认配置方式可以直接用于 openai 协议的结果缓存，同时支持流式和非流式响应的缓存。
 
+**提示**
+
+携带请求头`x-higress-skip-ai-cache: on`时，当前请求将不会使用缓存中的内容，而是直接转发给后端服务，同时也不会缓存该请求返回响应的内容
+
+
 ## 运行属性
 
 插件执行阶段：`认证阶段`
diff --git a/plugins/wasm-go/extensions/ai-cache/README_EN.md b/plugins/wasm-go/extensions/ai-cache/README_EN.md
index 81099e509..754499599 100644
--- a/plugins/wasm-go/extensions/ai-cache/README_EN.md
+++ b/plugins/wasm-go/extensions/ai-cache/README_EN.md
@@ -6,6 +6,10 @@ description: AI Cache Plugin Configuration Reference
 ## Function Description
 LLM result caching plugin, the default configuration can be directly used for result caching under the OpenAI protocol, and it supports caching of both streaming and non-streaming responses.
 
+**Tips**
+
+When carrying the request header `x-higress-skip-ai-cache: on`, the current request will not use content from the cache but will be directly forwarded to the backend service. Additionally, the response content from this request will not be cached.
+
 ## Runtime Properties
 Plugin Execution Phase: `Authentication Phase`
 Plugin Execution Priority: `10`
diff --git a/plugins/wasm-go/extensions/ai-cache/main.go b/plugins/wasm-go/extensions/ai-cache/main.go
index dc5df1a6a..7886d5698 100644
--- a/plugins/wasm-go/extensions/ai-cache/main.go
+++ b/plugins/wasm-go/extensions/ai-cache/main.go
@@ -22,6 +22,7 @@ const (
 	ToolCallsContextKey      = "toolCalls"
 	StreamContextKey         = "stream"
 	DefaultCacheKeyPrefix    = "higress-ai-cache:"
+	SkipCacheHeader          = "x-higress-skip-ai-cache"
 )
 
 func main() {
@@ -172,6 +173,12 @@ func parseConfig(json gjson.Result, c *PluginConfig, log wrapper.Log) error {
 }
 
 func onHttpRequestHeaders(ctx wrapper.HttpContext, config PluginConfig, log wrapper.Log) types.Action {
+	skipCache, _ := proxywasm.GetHttpRequestHeader(SkipCacheHeader)
+	if skipCache == "on" {
+		ctx.SetContext(SkipCacheHeader, struct{}{})
+		ctx.DontReadRequestBody()
+		return types.ActionContinue
+	}
 	contentType, _ := proxywasm.GetHttpRequestHeader("content-type")
 	// The request does not have a body.
 	if contentType == "" {
@@ -270,6 +277,11 @@ func processSSEMessage(ctx wrapper.HttpContext, config PluginConfig, sseMessage
 }
 
 func onHttpResponseHeaders(ctx wrapper.HttpContext, config PluginConfig, log wrapper.Log) types.Action {
+	skipCache := ctx.GetContext(SkipCacheHeader)
+	if skipCache != nil {
+		ctx.DontReadResponseBody()
+		return types.ActionContinue
+	}
 	contentType, _ := proxywasm.GetHttpResponseHeader("content-type")
 	if strings.Contains(contentType, "text/event-stream") {
 		ctx.SetContext(StreamContextKey, struct{}{})