diff --git a/docs/Endpoints/ChatCompletionAPI.md b/docs/Endpoints/ChatCompletionAPI.md
new file mode 100644
index 0000000..6523261
--- /dev/null
+++ b/docs/Endpoints/ChatCompletionAPI.md
@@ -0,0 +1,61 @@
+---
+sidebar_position: 1
+id: chat-completion-api
+title: Chat Completion API
+tags:
+  - OpenAI API
+  - Chat Models
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+## Chat Completion API
+
+**The role and the content of the prompt for each role is required.**
+
+<Tabs>
+  <TabItem value="py" label="Python" default>
+    ```python showLineNumbers
+    model = "Llama-3.1-70B-Instruct"  # choose one of available LLM (not the embedding model)
+    stream = True 
+
+    chat_response = client.chat.completions.create(
+        model=model,
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant named Llama-3."},
+            {"role": "user", "content": "What is Open Telekom Cloud?"},
+        ],
+        temperature=0.1,
+        max_tokens=256,
+        stream=stream
+    )
+
+    if not stream:
+        print(chat_response.choices[0].message.content)
+    else:
+        for chunk in chat_response:
+            if chunk.choices:
+                if chunk.choices[0].delta.content is not None:
+                    print(chunk.choices[0].delta.content, end="", flush=True)
+    ```
+  </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/chat/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "Llama-3.1-70B-Instruct",
+        "messages": [
+            {"role": "system", "content": "You are a helpful assistant named Llama-3."},
+            {"role": "user", "content": "What is Open Telekom Cloud?"}
+        ],
+        "temperature": 0.1,
+        "max_tokens": 256,
+        "stream": true
+    }'
+    ```
+  </TabItem>
+</Tabs>
diff --git a/docs/Endpoints/CompletionAPI.md b/docs/Endpoints/CompletionAPI.md
new file mode 100644
index 0000000..d26b423
--- /dev/null
+++ b/docs/Endpoints/CompletionAPI.md
@@ -0,0 +1,56 @@
+---
+sidebar_position: 2
+id: completion-api
+title: Completion API
+tags:
+  - OpenAI API
+  - Text Models
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+## Completion API
+
+**With this API, the raw text will be sent directly to the LLM without a special tag template.**
+
+<Tabs>
+  <TabItem value="py" label="Python" default>
+    ```python showLineNumbers
+    model = "Llama-3.1-70B-Instruct"  # choose one of the available LLMs (not the embedding model)
+    stream = True 
+
+    completion = client.completions.create(
+        model=model,
+        prompt="What is Python programming language?",
+        stream=stream,
+        temperature=0.2,
+        max_tokens=128
+    )
+
+    if not stream:
+        print(completion.choices[0].text)
+
+    else:
+        for chunk in completion:
+            if chunk.choices:
+                if chunk.choices[0].text is not None:
+                    print(chunk.choices[0].text, end="", flush=True)
+    ```
+  </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "Llama-3.1-70B-Instruct",
+        "prompt": "What is Python programming language?",
+        "temperature": 0.2,
+        "max_tokens": 128,
+        "stream": true
+    }'
+    ```
+  </TabItem>
+</Tabs>
diff --git a/docs/Endpoints/EmbeddingAPI.md b/docs/Endpoints/EmbeddingAPI.md
new file mode 100644
index 0000000..f30c0e3
--- /dev/null
+++ b/docs/Endpoints/EmbeddingAPI.md
@@ -0,0 +1,42 @@
+---
+sidebar_position: 3
+id: embedding-api
+title: Embedding API
+tags:
+  - OpenAI API
+  - Embedding Models
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+## Embedding API
+
+<Tabs>
+  <TabItem value="py" label="Python" default>
+    ```python showLineNumbers
+    model = "jina-embeddings-v2-base-de"
+
+    texts = ["I am Batman and I'm rich", "I am Spiderman", "I am Ironman and I'm a billionaire", "I am Flash", "I am the president of USA"]
+    embeddings = client.embeddings.create(
+        input=texts, model=model
+    )
+
+    print('Embedding dimension: ', len(embeddings.data[0].embedding))
+    print('Number of embedding vectors: ', len(embeddings.data))
+    print('Token usage: ', embeddings.usage)
+    ```
+  </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/embeddings \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "jina-embeddings-v2-base-de",
+        "input": ["I am Batman and I'm rich", "I am Spiderman", "I am Ironman and I'm a billionaire", "I am Flash", "I am the president of USA"]
+    }'
+    ```
+  </TabItem>
+</Tabs>
diff --git a/docs/Endpoints/_category_.json b/docs/Endpoints/_category_.json
new file mode 100644
index 0000000..e7c32c0
--- /dev/null
+++ b/docs/Endpoints/_category_.json
@@ -0,0 +1,8 @@
+{
+  "label": "Endpoints",
+  "position": 5,
+  "link": {
+    "type": "generated-index",
+    "description": "List of available Endpoints in AI Foundation Sevices"
+  }
+}
diff --git a/docs/Model Serving/API Reference.md b/docs/Model Serving/API Reference.md
index bdefb53..d3c8e09 100644
--- a/docs/Model Serving/API Reference.md	
+++ b/docs/Model Serving/API Reference.md	
@@ -49,6 +49,13 @@ pip install openai
       print(model.id)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X GET https://llm-server.llmhub.t-systems.net/v2/models \
+    -H "Authorization: Bearer YOUR_API_KEY"
+    ```
+  </TabItem>
 </Tabs>
 
 :::info
@@ -124,6 +131,24 @@ That will output:
                     print(chunk.choices[0].delta.content, end="", flush=True)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/chat/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "Llama-3.1-70B-Instruct",
+        "messages": [
+            {"role": "system", "content": "You are a helpful assistant named Llama-3."},
+            {"role": "user", "content": "What is Open Telekom Cloud?"}
+        ],
+        "temperature": 0.1,
+        "max_tokens": 256,
+        "stream": true
+    }'
+    ```
+  </TabItem>
 </Tabs>
 
 ### Completion API 
@@ -132,29 +157,42 @@ That will output:
 
 <Tabs>
   <TabItem value="py" label="Python" default>
+    ```python showLineNumbers
+    model = "Llama-3.1-70B-Instruct"  # choose one of the available LLMs (not the embedding model)
+    stream = True 
 
-```python showLineNumbers
-model = "Llama-3.1-70B-Instruct"  # choose one of the available LLMs (not the embedding model)
-stream = True 
-
-completion = client.completions.create(
-    model=model,
-    prompt="What is Python programming language?",
-    stream=stream,
-    temperature=0.2,
-    max_tokens=128
-)
-
-if not stream:
-    print(completion.choices[0].text)
-
-else:
-    for chunk in completion:
-        if chunk.choices:
-            if chunk.choices[0].text is not None:
-                print(chunk.choices[0].text, end="", flush=True)
-```
+    completion = client.completions.create(
+        model=model,
+        prompt="What is Python programming language?",
+        stream=stream,
+        temperature=0.2,
+        max_tokens=128
+    )
+
+    if not stream:
+        print(completion.choices[0].text)
 
+    else:
+        for chunk in completion:
+            if chunk.choices:
+                if chunk.choices[0].text is not None:
+                    print(chunk.choices[0].text, end="", flush=True)
+    ```
+  </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "Llama-3.1-70B-Instruct",
+        "prompt": "What is Python programming language?",
+        "temperature": 0.2,
+        "max_tokens": 128,
+        "stream": true
+    }'
+    ```
   </TabItem>
 </Tabs>
 
@@ -181,6 +219,18 @@ The completions API is only available for open-source models. To get the correct
     print('Token usage: ',embeddings.usage)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/embeddings \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "jina-embeddings-v2-base-de",
+        "input": ["I am Batman and I'm rich","I am Spiderman","I am Ironman and I'm a bilionaire", "I am Flash", "I am the president of USA"]
+    }'
+    ```
+  </TabItem>
 </Tabs>
 
 Example output:
@@ -207,7 +257,9 @@ Usage(prompt_tokens=31, total_tokens=31)
                 "properties": {
                     "location": {
                         "type": "string",
-                        "description": "The city and state, e.g. San Francisco, CA",
+                        "description":
+
+ "The city and state, e.g. San Francisco, CA",
                     },
                     "format": {
                         "type": "string",
@@ -233,6 +285,45 @@ Usage(prompt_tokens=31, total_tokens=31)
     print(assistant_message)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/chat/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "gpt-4-turbo-128k-france",
+        "messages": [
+            {"role": "system", "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."},
+            {"role": "user", "content": "What's the weather like today in Hamburg"}
+        ],
+        "tools": [
+            {
+                "type": "function",
+                "function": {
+                    "name": "get_current_weather",
+                    "description": "Get the current weather",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA"
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use."
+                            }
+                        },
+                        "required": ["location", "format"]
+                    }
+                }
+            }
+        ]
+    }'
+    ```
+  </TabItem>
 </Tabs>
 
 Example output:
@@ -272,6 +363,13 @@ Here is an example of how to use OpenAI Vision API for Llava-1.6-34b.
       print(model.id)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X GET https://llm-server.llmhub.t-systems.net/vision/models \
+    -H "Authorization: Bearer YOUR_API_KEY"
+    ```
+  </TabItem>
 </Tabs>
 
 Example output:
@@ -327,6 +425,32 @@ llava-v1.6-vicuna-13b
         print(chat_response.choices[0].message.content)
     ```
   </TabItem>
+
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/vision/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "llava-v1.6-vicuna-13b",
+        "messages": [
+            {
+                "role": "system",
+                "content": [{"type": "text", "text": "You are an helpful AI assistant named LLava help people answer their question base on the image and text provided."}]
+            },
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "What’s in this image?"},
+                    {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"}}
+                ]
+            }
+        ],
+        "max_tokens": 300,
+        "temperature": 0.01
+    }'
+    ```
+  </TabItem>
 </Tabs>
 
 Example output:
@@ -400,7 +524,37 @@ The overall scene is peaceful and invites one to imagine a walk through the fiel
                 if chunk.choices[0].delta.content is not None:
                     print(chunk.choices[0].delta.content, end="")
     else:
-        print(chat_response.choices[0].message.content)
+        print(chat_response
+
+.choices[0].message.content)
     ```
   </TabItem>
-</Tabs>
+  <TabItem value="curl" label="cURL">
+    ```bash showLineNumbers
+    curl -X POST https://llm-server.llmhub.t-systems.net/v2/chat/completions \
+    -H "Authorization: Bearer YOUR_API_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+      "model": "llava-v1.6-34b",
+      "messages": [
+        {
+          "role": "user",
+          "content": [
+            {"type": "text", "text": "What’s in this image?"},
+            {
+              "type": "image_url",
+              "image_url": {
+                "url": "data:image/jpeg;base64,YOUR_BASE64_IMAGE_STRING"
+              }
+            }
+          ]
+        }
+      ],
+      "max_tokens": 1000,
+      "temperature": 0.01,
+      "stream": true
+    }'
+    ```
+  </TabItem>
+
+</Tabs>
\ No newline at end of file
diff --git a/docs/Model Serving/Audio API.md b/docs/Model Serving/Audio API.md
index 63e129a..2f83417 100644
--- a/docs/Model Serving/Audio API.md	
+++ b/docs/Model Serving/Audio API.md	
@@ -1,7 +1,7 @@
 ---
 sidebar_position: 5  
 id: audio-api  
-title: Audio API Reference  
+title: Audio API
 tags:  
   - Audio API  
   - Transcription  
@@ -26,7 +26,7 @@ To interact with the audio API, set up your environment variables as follows:
 
 ```bash
 # Set API base URL
-export API_BASE=https://llm-server.llmhub.t-systems.net
+export API_BASE=https://llm-server.llmhub.t-systems.net/v2
 
 # Set your API key
 export API_KEY=YOUR_LLMHUB_KEY
diff --git a/package-lock.json b/package-lock.json
index a1a0a81..ab81a4d 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -8,7 +8,7 @@
       "name": "my-website",
       "version": "0.0.0",
       "dependencies": {
-        "@docusaurus/core": "3.2.1",
+        "@docusaurus/core": "^3.2.1",
         "@docusaurus/preset-classic": "3.2.1",
         "@easyops-cn/docusaurus-search-local": "^0.40.1",
         "@mdx-js/react": "^3.0.0",
@@ -3127,6 +3127,7 @@
       "version": "3.2.1",
       "resolved": "https://registry.npmjs.org/@docusaurus/core/-/core-3.2.1.tgz",
       "integrity": "sha512-ZeMAqNvy0eBv2dThEeMuNzzuu+4thqMQakhxsgT5s02A8LqRcdkg+rbcnuNqUIpekQ4GRx3+M5nj0ODJhBXo9w==",
+      "license": "MIT",
       "dependencies": {
         "@babel/core": "^7.23.3",
         "@babel/generator": "^7.23.3",
@@ -6435,9 +6436,10 @@
       }
     },
     "node_modules/cross-spawn": {
-      "version": "7.0.3",
-      "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.3.tgz",
-      "integrity": "sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==",
+      "version": "7.0.6",
+      "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
+      "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
+      "license": "MIT",
       "dependencies": {
         "path-key": "^3.1.0",
         "shebang-command": "^2.0.0",
diff --git a/package.json b/package.json
index e0a7a9f..e40f4bd 100644
--- a/package.json
+++ b/package.json
@@ -14,7 +14,7 @@
     "write-heading-ids": "docusaurus write-heading-ids"
   },
   "dependencies": {
-    "@docusaurus/core": "3.2.1",
+    "@docusaurus/core": "^3.2.1",
     "@docusaurus/preset-classic": "3.2.1",
     "@easyops-cn/docusaurus-search-local": "^0.40.1",
     "@mdx-js/react": "^3.0.0",