diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml
index 44168014b..b7b6bd3c1 100644
--- a/docs/openapi/jan.yaml
+++ b/docs/openapi/jan.yaml
@@ -67,21 +67,18 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: >
-            curl http://localhost:1337/v1/chat/completions \
-              -H "Content-Type: application/json" \
-              -d '{
-                "model": "tinyllama-1.1b",
-                "messages": [
-                  {
-                    "role": "system",
-                    "content": "You are a helpful assistant."
-                  },
-                  {
-                    "role": "user",
-                    "content": "Hello!"
-                  }
-                ]
-              }'
+            curl -X POST
+            'http://localhost:3982/inferences/llamacpp/chat_completion' \
+                  -H "Content-Type: application/json" \
+                  -d '{
+                    "llama_model_path": "/path/to/your/model.gguf",
+                    "messages": [
+                      {
+                        "role": "user",
+                        "content": "hello"
+                      },
+                    ]
+                  }'
   /models:
     get:
       operationId: listModels
diff --git a/docs/openapi/specs/chat.yaml b/docs/openapi/specs/chat.yaml
index 48b863ed1..9303e9713 100644
--- a/docs/openapi/specs/chat.yaml
+++ b/docs/openapi/specs/chat.yaml
@@ -71,13 +71,13 @@ components:
           description: |
             Contains input data or prompts for the model to process.
           example:
-            - content: "You are a helpful assistant."
-              role: system
-            - content: Hello!
+            - content: "Hello there :wave:"
+              role: assistant
+            - content: Can you write a long story
               role: user
         model:
           type: string
-          example: tinyllama-1.1b
+          example: model-zephyr-7B
           description: |
             Specifies the model being used for inference or processing tasks.
         stream: