docs(customers.md): add customer cost tracking to docs

docs/my-website/docs/proxy/customers.md

@@ -0,0 +1,50 @@
+# 🙋‍♂️ Customers 
+
+Track spend, set budgets for your customers.
+
+## Tracking Customer Credit
+
+1. Track LLM API Spend by Customer ID
+
+Make a /chat/completions call, pass 'user' - First call Works
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+        --header 'Content-Type: application/json' \
+        --header 'Authorization: Bearer sk-1234' \ # 👈 YOUR PROXY KEY
+        --data ' {
+        "model": "azure-gpt-3.5",
+        "user": "ishaan3", # 👈 CUSTOMER ID
+        "messages": [
+            {
+            "role": "user",
+            "content": "what time is it"
+            }
+        ]
+        }'
+```
+
+The customer_id will be upserted into the DB with the new spend.
+
+If the customer_id already exists, spend will be incremented.
+
+2. Get Customer Spend 
+
+```bash
+curl -X GET 'http://0.0.0.0:4000/customer/info?end_user_id=ishaan3' \ # 👈 CUSTOMER ID
+        -H 'Authorization: Bearer sk-1234' \ # 👈 YOUR PROXY KEY
+```
+
+Expected Response:
+
+```
+{
+    "user_id": "ishaan3",
+    "blocked": false,
+    "alias": null,
+    "spend": 0.001413,
+    "allowed_model_region": null,
+    "default_model": null,
+    "litellm_budget_table": null
+}
+```

docs/my-website/sidebars.js

@@ -41,6 +41,7 @@ const sidebars = {
         "proxy/reliability",
         "proxy/cost_tracking",
         "proxy/users",
+        "proxy/customers",
         "proxy/billing",
         "proxy/user_keys",
         "proxy/enterprise",

litellm/batches/main.py

@@ -348,7 +348,7 @@ async def acreate_batch(
 
 def create_batch(
     completion_window: Literal["24h"],
-    endpoint: Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
+    endpoint: Literal["/v1/chat/completions", "/v1/embeddings"],
     input_file_id: str,
     custom_llm_provider: Literal["openai"] = "openai",
     metadata: Optional[Dict[str, str]] = None,

litellm/proxy/proxy_server.py

@@ -8412,6 +8412,7 @@ async def new_end_user(
     "/customer/info",
     tags=["Customer Management"],
     dependencies=[Depends(user_api_key_auth)],
+    response_model=LiteLLM_EndUserTable,
 )
 @router.get(
     "/end_user/info",
@@ -8436,7 +8437,12 @@ async def end_user_info(
         where={"user_id": end_user_id}
     )
 
-    return user_info
+    if user_info is None:
+        raise HTTPException(
+            status_code=400,
+            detail={"error": "End User Id={} does not exist in db".format(end_user_id)},
+        )
+    return user_info.model_dump(exclude_none=True)
 
 
 @router.post(

litellm/types/llms/openai.py

@@ -214,7 +214,7 @@ class CreateBatchRequest(TypedDict, total=False):
     """
 
     completion_window: Literal["24h"]
-    endpoint: Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"]
+    endpoint: Literal["/v1/chat/completions", "/v1/embeddings"]
     input_file_id: str
     metadata: Optional[Dict[str, str]]
     extra_headers: Optional[Dict[str, str]]