docs(custom_llm_server.md): document anthropic custom llm translation

docs/my-website/docs/providers/custom_llm_server.md

@@ -13,11 +13,12 @@ Call your custom torch-serve / internal LLM APIs via LiteLLM
 :::
 
 Supported Routes:
-- `/v1/chat/completions` -> `litellm.completion`
-- `/v1/completions` -> `litellm.text_completion`
-- `/v1/embeddings` -> `litellm.embedding`
-- `/v1/images/generations` -> `litellm.image_generation`
+- `/v1/chat/completions` -> `litellm.acompletion`
+- `/v1/completions` -> `litellm.atext_completion`
+- `/v1/embeddings` -> `litellm.aembedding`
+- `/v1/images/generations` -> `litellm.aimage_generation`
 
+- `/v1/messages` -> `litellm.acompletion`
 
 ## Quick Start 
 
@@ -262,6 +263,102 @@ Expected Response
 }
 ```
 
+## Anthropic `/v1/messages`
+
+- Write the integration for .acompletion
+- litellm will transform it to /v1/messages
+
+1. Setup your `custom_handler.py` file 
+
+```python
+import litellm
+from litellm import CustomLLM, completion, get_llm_provider
+
+
+class MyCustomLLM(CustomLLM):
+    async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+
+my_custom_llm = MyCustomLLM()
+```
+
+2. Add to `config.yaml` 
+
+In the config below, we pass
+
+python_filename: `custom_handler.py`
+custom_handler_instance_name: `my_custom_llm`. This is defined in Step 1
+
+custom_handler: `custom_handler.my_custom_llm`
+
+```yaml
+model_list:
+  - model_name: "test-model"             
+    litellm_params:
+      model: "openai/text-embedding-ada-002"
+  - model_name: "my-custom-model"
+    litellm_params:
+      model: "my-custom-llm/my-model"
+
+litellm_settings:
+  custom_provider_map:
+  - {"provider": "my-custom-llm", "custom_handler": custom_handler.my_custom_llm}
+```
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/messages' \
+-H 'anthropic-version: 2023-06-01' \
+-H 'content-type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+   "model": "my-custom-model",
+     "max_tokens": 1024,
+     "messages": [{
+         "role": "user",
+         "content": [
+         {
+             "type": "text",
+             "text": "What are the key findings in this document 12?"
+         }]
+     }]
+}'
+```
+
+Expected Response
+
+```json
+{
+    "id": "chatcmpl-Bm4qEp4h4vCe7Zi4Gud1MAxTWgibO",
+    "type": "message",
+    "role": "assistant",
+    "model": "gpt-3.5-turbo-0125",
+    "stop_sequence": null,
+    "usage": {
+        "input_tokens": 18,
+        "output_tokens": 44
+    },
+    "content": [
+        {
+            "type": "text",
+            "text": "Without the specific document being provided, it is not possible to determine the key findings within it. If you can provide the content or a summary of document 12, I would be happy to help identify the key findings."
+        }
+    ],
+    "stop_reason": "end_turn"
+}
+```
+
+
 ## Additional Parameters
 
 Additional parameters are passed inside `optional_params` key in the `completion` or `image_generation` function.