diff --git a/api_llm_gateway.http b/api_llm_gateway.http
new file mode 100644
index 00000000..b40c229b
--- /dev/null
+++ b/api_llm_gateway.http
@@ -0,0 +1,76 @@
+@llm_endpoint = http://localhost:12000
+@openai_endpoint = https://api.openai.com
+@access_key = {{$dotenv OPENAI_API_KEY}}
+
+### openai request
+POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+Authorization: Bearer {{access_key}}
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "hello"
+    }
+  ],
+  "model": "gpt-4o-mini"
+}
+
+### openai request (streaming)
+POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+Authorization: Bearer {{access_key}}
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "hello"
+    }
+  ],
+  "model": "gpt-4o-mini",
+  "stream": true
+}
+
+
+### llm gateway request
+POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "hello"
+    }
+  ]
+}
+
+### llm gateway request (streaming)
+POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "hello"
+    }
+  ],
+  "stream": true
+}
+
+### llm gateway request (provider hint)
+POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+x-arch-llm-provider-hint: gpt-3.5-turbo-0125
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "hello"
+    }
+  ]
+}
diff --git a/api_prompt_gateway.http b/api_prompt_gateway.http
new file mode 100644
index 00000000..b79b4230
--- /dev/null
+++ b/api_prompt_gateway.http
@@ -0,0 +1,87 @@
+@prompt_endpoint = http://localhost:10000
+
+### prompt gateway request
+POST {{prompt_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "how is the weather in seattle for next 10 days"
+    }
+  ]
+}
+
+### prompt gateway request (streaming)
+POST {{prompt_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "how is the weather in seattle for next 10 days"
+    }
+  ],
+  "stream": true
+}
+
+
+### prompt gateway request param gathering
+POST {{prompt_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "how is the weather in seattle"
+    }
+  ]
+}
+
+### prompt gateway request param gathering and function calling
+POST {{prompt_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "how is the weather in seattle"
+    },
+    {
+      "role": "assistant",
+      "content": "It seems I'm missing some information. Could you provide the following details days ?",
+      "model": "Arch-Function-1.5b"
+    },
+    {
+      "role": "user",
+      "content": "for next 10 days"
+    }
+  ]
+}
+
+### prompt gateway request param gathering and function calling (streaming)
+POST {{prompt_endpoint}}/v1/chat/completions HTTP/1.1
+Content-Type: application/json
+
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "how is the weather in seattle"
+    },
+    {
+      "role": "assistant",
+      "content": "It seems I'm missing some information. Could you provide the following details days ?",
+      "model": "Arch-Function-1.5b"
+    },
+    {
+      "role": "user",
+      "content": "for next 10 days"
+    }
+  ],
+  "stream": true
+}