diff --git a/test/e2e/conformance/tests/go-wasm-ai-proxy.go b/test/e2e/conformance/tests/go-wasm-ai-proxy.go
index 653c54ac9..398d1e8a2 100644
--- a/test/e2e/conformance/tests/go-wasm-ai-proxy.go
+++ b/test/e2e/conformance/tests/go-wasm-ai-proxy.go
@@ -777,6 +777,66 @@ data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"？"},
 
 data: [DONE]
 
+`),
+					},
+				},
+			},
+			{
+				Meta: http.AssertionMeta{
+					TestCaseName:  "cloudflare case 1: non-streaming request",
+					CompareTarget: http.CompareTargetResponse,
+				},
+				Request: http.AssertionRequest{
+					ActualRequest: http.Request{
+						Host:        "api.cloudflare.com",
+						Path:        "/v1/chat/completions",
+						Method:      "POST",
+						ContentType: http.ContentTypeApplicationJson,
+						Body:        []byte(`{"model":"gpt-3","messages":[{"role":"user","content":"你好，你是谁？"}],"stream":false}`),
+					},
+				},
+				Response: http.AssertionResponse{
+					ExpectedResponse: http.Response{
+						StatusCode:  200,
+						ContentType: http.ContentTypeApplicationJson,
+						Body:        []byte(`{"id":"chatcmpl-llm-mock","choices":[{"index":0,"message":{"role":"assistant","content":"你好，你是谁？"},"finish_reason":"stop","logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion","usage":{"prompt_tokens":9,"completion_tokens":1,"total_tokens":10}}`),
+					},
+				},
+			},
+			{
+				Meta: http.AssertionMeta{
+					TestCaseName:  "cloudflare case 2: streaming request",
+					CompareTarget: http.CompareTargetResponse,
+				},
+				Request: http.AssertionRequest{
+					ActualRequest: http.Request{
+						Host:        "api.cloudflare.com",
+						Path:        "/v1/chat/completions",
+						Method:      "POST",
+						ContentType: http.ContentTypeApplicationJson,
+						Body:        []byte(`{"model":"gpt-3","messages":[{"role":"user","content":"你好，你是谁？"}],"stream":true}`),
+					},
+				},
+				Response: http.AssertionResponse{
+					ExpectedResponse: http.Response{
+						StatusCode:  200,
+						ContentType: http.ContentTypeTextEventStream,
+						Body: []byte(`data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"，"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"是"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"谁"},"finish_reason":null,"logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: {"id":"chatcmpl-llm-mock","choices":[{"index":0,"delta":{"content":"？"},"finish_reason":"stop","logprobs":null}],"created":10,"model":"meta/llama-3.1-8b-instruct","object":"chat.completion.chunk","usage":null}
+
+data: [DONE]
+
 `),
 					},
 				},
diff --git a/test/e2e/conformance/tests/go-wasm-ai-proxy.yaml b/test/e2e/conformance/tests/go-wasm-ai-proxy.yaml
index 64c081701..57ed580ce 100644
--- a/test/e2e/conformance/tests/go-wasm-ai-proxy.yaml
+++ b/test/e2e/conformance/tests/go-wasm-ai-proxy.yaml
@@ -260,6 +260,25 @@ spec:
 ---
 apiVersion: networking.k8s.io/v1
 kind: Ingress
+metadata:
+  name: wasmplugin-ai-proxy-cloudflare
+  namespace: higress-conformance-ai-backend
+spec:
+  ingressClassName: higress
+  rules:
+    - host: "api.cloudflare.com"
+      http:
+        paths:
+          - pathType: Prefix
+            path: "/"
+            backend:
+              service:
+                name: llm-mock-service
+                port:
+                  number: 3000
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
 metadata:
   name: wasmplugin-ai-proxy-together-ai
   namespace: higress-conformance-ai-backend
@@ -520,6 +539,16 @@ spec:
           type: stepfun
       ingress:
         - higress-conformance-ai-backend/wasmplugin-ai-proxy-stepfun
+    - config:
+        provider:
+          apiTokens:
+            - fake_token
+          modelMapping:
+            "gpt-3": meta/llama-3.1-8b-instruct
+            "*": meta/llama-3.1-70b-instruct
+          type: cloudflare
+      ingress:
+        - higress-conformance-ai-backend/wasmplugin-ai-proxy-cloudflare
     - config:
         provider:
           apiTokens: