Merge pull request #2416 from BerriAI/litellm_use_consistent_port

(docs) LiteLLM Proxy - use port 4000 in examples

README.md

@@ -143,13 +143,13 @@ pip install 'litellm[proxy]'
 ```shell
 $ litellm --model huggingface/bigcode/starcoder
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 ### Step 2: Make ChatCompletions Request to Proxy
 ```python
 import openai # openai v1.0.0+
-client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:8000") # set proxy to base_url
+client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:4000") # set proxy to base_url
 # request sent to model set on litellm proxy, `litellm --model`
 response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
     {
@@ -170,7 +170,7 @@ Set budgets and rate limits across multiple projects
 
 ### Request
 ```shell
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data-raw '{"models": ["gpt-3.5-turbo", "gpt-4", "claude-2"], "duration": "20m","metadata": {"user": "ishaan@berri.ai", "team": "core-infra"}}'

deploy/charts/litellm/README.md

@@ -28,7 +28,7 @@ If `db.useStackgresOperator` is used (not yet implemented):
 | `imagePullSecrets`                                         | Registry credentials for the LiteLLM and initContainer images.                                                                                                                        | `[]`  |
 | `serviceAccount.create`                                    | Whether or not to create a Kubernetes Service Account for this deployment.  The default is `false` because LiteLLM has no need to access the Kubernetes API.                          | `false`  |
 | `service.type`                                             | Kubernetes Service type (e.g. `LoadBalancer`, `ClusterIP`, etc.)                                                                                                                      | `ClusterIP`  |
-| `service.port`                                             | TCP port that the Kubernetes Service will listen on.  Also the TCP port within the Pod that the proxy will listen on.                                                                 | `8000`  |
+| `service.port`                                             | TCP port that the Kubernetes Service will listen on.  Also the TCP port within the Pod that the proxy will listen on.                                                                 | `4000`  |
 | `ingress.*`                                                | See [values.yaml](./values.yaml) for example settings                                                                                                                                 | N/A  |
 | `proxy_config.*`                                           | See [values.yaml](./values.yaml) for default settings.  See [example_config_yaml](../../../litellm/proxy/example_config_yaml/) for configuration examples.                            | N/A  |
 
@@ -76,7 +76,7 @@ When browsing to the URL published per the settings in `ingress.*`, you will
 be prompted for **Admin Configuration**.  The **Proxy Endpoint** is the internal
 (from the `litellm` pod's perspective) URL published by the `<RELEASE>-litellm`
 Kubernetes Service.  If the deployment uses the default settings for this
-service, the **Proxy Endpoint** should be set to `http://<RELEASE>-litellm:8000`.
+service, the **Proxy Endpoint** should be set to `http://<RELEASE>-litellm:4000`.
 
 The **Proxy Key** is the value specified for `masterkey` or, if a `masterkey`
 was not provided to the helm command line, the `masterkey` is a randomly

deploy/charts/litellm/values.yaml

@@ -55,7 +55,7 @@ environmentSecrets: []
 
 service:
   type: ClusterIP
-  port: 8000
+  port: 4000
 
 ingress:
   enabled: false

docs/my-website/docs/embedding/supported_embedding.md

@@ -35,7 +35,7 @@ general_settings:
 ```bash
 litellm --config /path/to/config.yaml 
 
-# RUNNING on http://0.0.0.0:8000
+# RUNNING on http://0.0.0.0:4000
 ```
 
 ### Test 
@@ -44,7 +44,7 @@ litellm --config /path/to/config.yaml
 <TabItem value="curl" label="Curl">
 
 ```bash
-curl --location 'http://0.0.0.0:8000/embeddings' \
+curl --location 'http://0.0.0.0:4000/embeddings' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{"input": ["Academia.edu uses"], "model": "textembedding-gecko", "encoding_format": "base64"}'
@@ -57,7 +57,7 @@ curl --location 'http://0.0.0.0:8000/embeddings' \
 from openai import OpenAI
 client = OpenAI(
   api_key="sk-1234",
-  base_url="http://0.0.0.0:8000"
+  base_url="http://0.0.0.0:4000"
 )
 
 client.embeddings.create(
@@ -72,7 +72,7 @@ client.embeddings.create(
 ```python
 from langchain_openai import OpenAIEmbeddings
 
-embeddings = OpenAIEmbeddings(model="textembedding-gecko", openai_api_base="http://0.0.0.0:8000", openai_api_key="sk-1234")
+embeddings = OpenAIEmbeddings(model="textembedding-gecko", openai_api_base="http://0.0.0.0:4000", openai_api_key="sk-1234")
 
 text = "This is a test document."
 
@@ -200,7 +200,7 @@ Use this for calling `/embedding` endpoints on OpenAI Compatible Servers, exampl
 from litellm import embedding
 response = embedding(
   model = "openai/<your-llm-name>",     # add `openai/` prefix to model so litellm knows to route to OpenAI
-  api_base="http://0.0.0.0:8000/"       # set API Base of your Custom OpenAI Endpoint
+  api_base="http://0.0.0.0:4000/"       # set API Base of your Custom OpenAI Endpoint
   input=["good morning from litellm"]
 )
 ```

docs/my-website/docs/index.md

@@ -375,13 +375,13 @@ pip install 'litellm[proxy]'
 ```shell
 $ litellm --model huggingface/bigcode/starcoder
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 #### Step 2: Make ChatCompletions Request to Proxy
 ```python
 import openai # openai v1.0.0+
-client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:8000") # set proxy to base_url
+client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:4000") # set proxy to base_url
 # request sent to model set on litellm proxy, `litellm --model`
 response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
     {

docs/my-website/docs/load_test.md

@@ -90,7 +90,7 @@ import time, asyncio, litellm
 #### LITELLM PROXY #### 
 litellm_client = AsyncOpenAI(
     api_key="sk-1234", # [CHANGE THIS]
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 #### AZURE OPENAI CLIENT #### 

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

@@ -63,7 +63,7 @@ export ANTHROPIC_API_KEY="your-api-key"
 ```bash
 $ litellm --model claude-3-opus-20240229
 
-# Server running on http://0.0.0.0:8000
+# Server running on http://0.0.0.0:4000
 ```
 
 ### 3. Test it
@@ -73,7 +73,7 @@ $ litellm --model claude-3-opus-20240229
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -93,7 +93,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -120,7 +120,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000", # set openai_api_base to the LiteLLM Proxy
+    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
     model = "gpt-3.5-turbo",
     temperature=0.1
 )

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

@@ -54,7 +54,7 @@ export AWS_REGION_NAME=""
 ```bash
 $ litellm --model anthropic.claude-3-sonnet-20240229-v1:0
 
-# Server running on http://0.0.0.0:8000
+# Server running on http://0.0.0.0:4000
 ```
 
 ### 3. Test it
@@ -64,7 +64,7 @@ $ litellm --model anthropic.claude-3-sonnet-20240229-v1:0
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -84,7 +84,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -111,7 +111,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000", # set openai_api_base to the LiteLLM Proxy
+    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
     model = "gpt-3.5-turbo",
     temperature=0.1
 )

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

@@ -183,7 +183,7 @@ On the docker container run the `test.py` file using `python3 test.py`
 ```python
 import openai
 
-api_base = f"http://0.0.0.0:8000" # base url for server
+api_base = f"http://0.0.0.0:4000" # base url for server
 
 openai.api_base = api_base
 openai.api_key = "temp-key"

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

@@ -15,7 +15,7 @@ import os
 response = litellm.completion(
     model="openai/mistral,               # add `openai/` prefix to model so litellm knows to route to OpenAI
     api_key="sk-1234",                  # api key to your openai compatible endpoint
-    api_base="http://0.0.0.0:8000",     # set API Base of your Custom OpenAI Endpoint
+    api_base="http://0.0.0.0:4000",     # set API Base of your Custom OpenAI Endpoint
     messages=[
                 {
                     "role": "user",
@@ -35,7 +35,7 @@ import os
 response = litellm.embedding(
     model="openai/GPT-J",               # add `openai/` prefix to model so litellm knows to route to OpenAI
     api_key="sk-1234",                  # api key to your openai compatible endpoint
-    api_base="http://0.0.0.0:8000",     # set API Base of your Custom OpenAI Endpoint
+    api_base="http://0.0.0.0:4000",     # set API Base of your Custom OpenAI Endpoint
     input=["good morning from litellm"]
 )
 print(response)

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

@@ -145,7 +145,7 @@ $ litellm --config /path/to/config.yaml
 
 Send the same request twice:
 ```shell
-curl http://0.0.0.0:8000/v1/chat/completions \
+curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -153,7 +153,7 @@ curl http://0.0.0.0:8000/v1/chat/completions \
      "temperature": 0.7
    }'
 
-curl http://0.0.0.0:8000/v1/chat/completions \
+curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -166,14 +166,14 @@ curl http://0.0.0.0:8000/v1/chat/completions \
 
 Send the same request twice:
 ```shell
-curl --location 'http://0.0.0.0:8000/embeddings' \
+curl --location 'http://0.0.0.0:4000/embeddings' \
   --header 'Content-Type: application/json' \
   --data ' {
   "model": "text-embedding-ada-002",
   "input": ["write a litellm poem"]
   }'
 
-curl --location 'http://0.0.0.0:8000/embeddings' \
+curl --location 'http://0.0.0.0:4000/embeddings' \
   --header 'Content-Type: application/json' \
   --data ' {
   "model": "text-embedding-ada-002",
@@ -227,7 +227,7 @@ from openai import OpenAI
 client = OpenAI(
     # This is the default and can be omitted
     api_key=os.environ.get("OPENAI_API_KEY"),
-		base_url="http://0.0.0.0:8000"
+		base_url="http://0.0.0.0:4000"
 )
 
 chat_completion = client.chat.completions.create(
@@ -255,7 +255,7 @@ from openai import OpenAI
 client = OpenAI(
     # This is the default and can be omitted
     api_key=os.environ.get("OPENAI_API_KEY"),
-		base_url="http://0.0.0.0:8000"
+		base_url="http://0.0.0.0:4000"
 )
 
 chat_completion = client.chat.completions.create(
@@ -281,7 +281,7 @@ from openai import OpenAI
 client = OpenAI(
     # This is the default and can be omitted
     api_key=os.environ.get("OPENAI_API_KEY"),
-		base_url="http://0.0.0.0:8000"
+		base_url="http://0.0.0.0:4000"
 )
 
 chat_completion = client.chat.completions.create(

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

@@ -63,7 +63,7 @@ litellm_settings:
 $ litellm /path/to/config.yaml
 ```
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --data ' {
     "model": "gpt-3.5-turbo",
     "messages": [
@@ -162,7 +162,7 @@ litellm_settings:
 $ litellm /path/to/config.yaml
 ```
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --data ' {
     "model": "gpt-3.5-turbo",
     "messages": [

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

@@ -15,7 +15,7 @@ Cli arguments,  --host, --port, --num_workers
     ```
 
 ## --port
-   - **Default:** `8000`
+   - **Default:** `4000`
    - The port to bind the server to.
    - **Usage:** 
      ```shell

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

@@ -13,7 +13,7 @@ Set model list, `api_base`, `api_key`, `temperature` & proxy server settings (`m
 | `general_settings`   | Server settings, example setting `master_key: sk-my_special_key` |
 | `environment_variables`   | Environment Variables example, `REDIS_HOST`, `REDIS_PORT` |
 
-**Complete List:** Check the Swagger UI docs on `<your-proxy-url>/#/config.yaml` (e.g. http://0.0.0.0:8000/#/config.yaml), for everything you can pass in the config.yaml.
+**Complete List:** Check the Swagger UI docs on `<your-proxy-url>/#/config.yaml` (e.g. http://0.0.0.0:4000/#/config.yaml), for everything you can pass in the config.yaml.
 
 
 ## Quick Start 
@@ -55,7 +55,7 @@ model_list:
   - model_name: vllm-models
     litellm_params:
       model: openai/facebook/opt-125m # the `openai/` prefix tells litellm it's openai compatible
-      api_base: http://0.0.0.0:8000
+      api_base: http://0.0.0.0:4000
       rpm: 1440
     model_info: 
       version: 2
@@ -91,7 +91,7 @@ Sends request to model where `model_name=gpt-3.5-turbo` on config.yaml.
 If multiple with `model_name=gpt-3.5-turbo` does [Load Balancing](https://docs.litellm.ai/docs/proxy/load_balancing)
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -111,7 +111,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 Sends this request to model where `model_name=bedrock-claude-v1` on config.yaml
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "bedrock-claude-v1",
@@ -131,7 +131,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # Sends request to model where `model_name=gpt-3.5-turbo` on config.yaml. 
@@ -179,7 +179,7 @@ messages = [
 
 # Sends request to model where `model_name=gpt-3.5-turbo` on config.yaml. 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000",  # set openai base to the proxy
+    openai_api_base="http://0.0.0.0:4000",  # set openai base to the proxy
     model = "gpt-3.5-turbo",                
     temperature=0.1
 )
@@ -189,7 +189,7 @@ print(response)
 
 # Sends request to model where `model_name=bedrock-claude-v1` on config.yaml. 
 claude_chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000", # set openai base to the proxy
+    openai_api_base="http://0.0.0.0:4000", # set openai base to the proxy
     model = "bedrock-claude-v1",                   
     temperature=0.1
 )
@@ -560,7 +560,7 @@ litellm --config config.yaml
 Sends Request to `bedrock-cohere`
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --data ' {
   "model": "bedrock-cohere",

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

@@ -254,10 +254,10 @@ helm install \
 kubectl \
   port-forward \
   service/mydeploy-litellm \
-  8000:8000
+  4000:4000
 ```
 
-Your OpenAI proxy server is now running on `http://127.0.0.1:8000`.
+Your OpenAI proxy server is now running on `http://127.0.0.1:4000`.
 
 </TabItem>
 </Tabs>
@@ -473,11 +473,11 @@ services:
           target: runtime
     image: ghcr.io/berriai/litellm:main-latest
     ports:
-      - "8000:8000" # Map the container port to the host, change the host port if necessary
+      - "4000:4000" # Map the container port to the host, change the host port if necessary
     volumes:
       - ./litellm-config.yaml:/app/config.yaml # Mount the local configuration file
     # You can change the port or number of workers as per your requirements or pass any new supported CLI augument. Make sure the port passed here matches with the container port defined above in `ports` value
-    command: [ "--config", "/app/config.yaml", "--port", "8000", "--num_workers", "8" ]
+    command: [ "--config", "/app/config.yaml", "--port", "4000", "--num_workers", "8" ]
 
 # ...rest of your docker-compose config if any
 ```
@@ -495,4 +495,4 @@ Run the command `docker-compose up` or `docker compose up` as per your docker in
 > Use `-d` flag to run the container in detached mode (background) e.g. `docker compose up -d`
 
 
-Your LiteLLM container should be running now on the defined port e.g. `8000`.
+Your LiteLLM container should be running now on the defined port e.g. `4000`.

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

@@ -38,7 +38,7 @@ $ litellm --config /path/to/config.yaml
 3. Test the embedding call
 
 ```shell
-curl --location 'http://0.0.0.0:8000/v1/embeddings' \
+curl --location 'http://0.0.0.0:4000/v1/embeddings' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{

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

@@ -58,7 +58,7 @@ callbacks: ["llamaguard_moderations"]
 Set the LLM Guard API Base in your environment 
 
 ```env
-LLM_GUARD_API_BASE = "http://0.0.0.0:8000"
+LLM_GUARD_API_BASE = "http://0.0.0.0:4000"
 ```
 
 Add `llmguard_moderations` as a callback 
@@ -143,7 +143,7 @@ When `no-log=True`, the request will **not be logged on any callbacks** and ther
 import openai
 client = openai.OpenAI(
     api_key="anything",            # proxy api-key
-    base_url="http://0.0.0.0:8000" # litellm proxy 
+    base_url="http://0.0.0.0:4000" # litellm proxy 
 )
 
 response = client.chat.completions.create(
@@ -175,7 +175,7 @@ litellm_settings:
 ### How to test
 
 ```bash 
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -202,7 +202,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 **Block all calls for a user id**
 
 ```
-curl -X POST "http://0.0.0.0:8000/user/block" \
+curl -X POST "http://0.0.0.0:4000/user/block" \
 -H "Authorization: Bearer sk-1234" \ 
 -D '{
 "user_ids": [<user_id>, ...] 
@@ -212,7 +212,7 @@ curl -X POST "http://0.0.0.0:8000/user/block" \
 **Unblock calls for a user id**
 
 ```
-curl -X POST "http://0.0.0.0:8000/user/unblock" \
+curl -X POST "http://0.0.0.0:4000/user/unblock" \
 -H "Authorization: Bearer sk-1234" \ 
 -D '{
 "user_ids": [<user_id>, ...] 
@@ -230,7 +230,7 @@ litellm_settings:
 ### Test this 
 
 ```bash
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -263,7 +263,7 @@ Set `extra_body={"metadata": { }}` to `metadata` you want to pass
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -291,7 +291,7 @@ print(response)
 Pass `metadata` as part of the request body
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data '{
     "model": "gpt-3.5-turbo",
@@ -317,7 +317,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000",
+    openai_api_base="http://0.0.0.0:4000",
     model = "gpt-3.5-turbo",
     temperature=0.1,
     extra_body={

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

@@ -12,10 +12,10 @@ The proxy exposes:
 #### Request
 Make a GET Request to `/health` on the proxy
 ```shell
-curl --location 'http://0.0.0.0:8000/health' -H "Authorization: Bearer sk-1234"
+curl --location 'http://0.0.0.0:4000/health' -H "Authorization: Bearer sk-1234"
 ```
 
-You can also run `litellm -health` it makes a `get` request to `http://0.0.0.0:8000/health` for you
+You can also run `litellm -health` it makes a `get` request to `http://0.0.0.0:4000/health` for you
 ```
 litellm --health
 ```
@@ -60,7 +60,7 @@ $ litellm /path/to/config.yaml
 
 3. Query health endpoint: 
 ```
-curl --location 'http://0.0.0.0:8000/health'
+curl --location 'http://0.0.0.0:4000/health'
 ```
 
 ### Embedding Models 
@@ -119,7 +119,7 @@ Unprotected endpoint for checking if proxy is ready to accept requests
 Example Request: 
 
 ```bash 
-curl --location 'http://0.0.0.0:8000/health/readiness'
+curl --location 'http://0.0.0.0:4000/health/readiness'
 ```
 
 Example Response:  
@@ -153,7 +153,7 @@ Example Request:
 
 ```
 curl -X 'GET' \
-  'http://0.0.0.0:8000/health/liveliness' \
+  'http://0.0.0.0:4000/health/liveliness' \
   -H 'accept: application/json'
 ```
 

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

@@ -45,7 +45,7 @@ $ litellm --config /path/to/config.yaml
 ### Step 3: Use proxy - Call a model group [Load Balancing]
 Curl Command
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -65,7 +65,7 @@ If you want to call a specific model defined in the `config.yaml`, you can call
 In this example it will call `azure/gpt-turbo-small-ca`. Defined in the config on Step 1
 
 ```bash
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "azure/gpt-turbo-small-ca",

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

@@ -150,7 +150,7 @@ litellm --config proxy_config.yaml
 ```
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Authorization: Bearer sk-1234' \
     --data ' {
     "model": "gpt-3.5-turbo",
@@ -174,7 +174,7 @@ On Success
     Usage: {'completion_tokens': 10, 'prompt_tokens': 11, 'total_tokens': 21},
     Cost: 3.65e-05,
     Response: {'id': 'chatcmpl-8S8avKJ1aVBg941y5xzGMSKrYCMvN', 'choices': [{'finish_reason': 'stop', 'index': 0, 'message': {'content': 'Good morning! How can I assist you today?', 'role': 'assistant'}}], 'created': 1701716913, 'model': 'gpt-3.5-turbo-0613', 'object': 'chat.completion', 'system_fingerprint': None, 'usage': {'completion_tokens': 10, 'prompt_tokens': 11, 'total_tokens': 21}}
-    Proxy Metadata: {'user_api_key': None, 'headers': Headers({'host': '0.0.0.0:8000', 'user-agent': 'curl/7.88.1', 'accept': '*/*', 'authorization': 'Bearer sk-1234', 'content-length': '199', 'content-type': 'application/x-www-form-urlencoded'}), 'model_group': 'gpt-3.5-turbo', 'deployment': 'gpt-3.5-turbo-ModelID-gpt-3.5-turbo'}
+    Proxy Metadata: {'user_api_key': None, 'headers': Headers({'host': '0.0.0.0:4000', 'user-agent': 'curl/7.88.1', 'accept': '*/*', 'authorization': 'Bearer sk-1234', 'content-length': '199', 'content-type': 'application/x-www-form-urlencoded'}), 'model_group': 'gpt-3.5-turbo', 'deployment': 'gpt-3.5-turbo-ModelID-gpt-3.5-turbo'}
 ```
 
 #### Logging Proxy Request Object, Header, Url
@@ -374,7 +374,7 @@ async def log_event(request: Request):
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="127.0.0.1", port=8000)
+    uvicorn.run(app, host="127.0.0.1", port=4000)
 
 
 ```
@@ -383,7 +383,7 @@ if __name__ == "__main__":
 #### Step 2. Set your `GENERIC_LOGGER_ENDPOINT` to the endpoint + route we should send callback logs to
 
 ```shell
-os.environ["GENERIC_LOGGER_ENDPOINT"] = "http://localhost:8000/log-event"
+os.environ["GENERIC_LOGGER_ENDPOINT"] = "http://localhost:4000/log-event"
 ```
 
 #### Step 3. Create a `config.yaml` file and set `litellm_settings`: `success_callback` = ["generic"]
@@ -445,7 +445,7 @@ Expected output on Langfuse
 Pass `metadata` as part of the request body
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data '{
     "model": "gpt-3.5-turbo",
@@ -472,7 +472,7 @@ Set `extra_body={"metadata": { }}` to `metadata` you want to pass
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -509,7 +509,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000",
+    openai_api_base="http://0.0.0.0:4000",
     model = "gpt-3.5-turbo",
     temperature=0.1,
     extra_body={
@@ -663,7 +663,7 @@ litellm --config config.yaml --debug
 
 Test Request
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data ' {
     "model": "Azure OpenAI GPT-4 East",
@@ -698,7 +698,7 @@ litellm_settings:
 Now, when you [generate keys](./virtual_keys.md) for this team-id 
 
 ```bash
-curl -X POST 'http://0.0.0.0:8000/key/generate' \
+curl -X POST 'http://0.0.0.0:4000/key/generate' \
 -H 'Authorization: Bearer sk-1234' \
 -H 'Content-Type: application/json' \
 -D '{"team_id": "ishaans-secret-project"}'
@@ -742,7 +742,7 @@ litellm --config config.yaml --debug
 
 Test Request
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data ' {
     "model": "Azure OpenAI GPT-4 East",
@@ -903,7 +903,7 @@ litellm --config config.yaml --debug
 
 Test Request
 ```
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data ' {
     "model": "gpt-3.5-turbo",
@@ -947,7 +947,7 @@ litellm --config config.yaml --debug
 
 Test Request
 ```
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data ' {
     "model": "gpt-3.5-turbo",

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

@@ -24,7 +24,7 @@ Retrieve detailed information about each model listed in the `/models` endpoint,
   <TabItem value="curl">
 
 ```bash
-curl -X GET "http://0.0.0.0:8000/model/info" \
+curl -X GET "http://0.0.0.0:4000/model/info" \
      -H "accept: application/json" \
 ```
   </TabItem>
@@ -42,7 +42,7 @@ Add a new model to the list in the `config.yaml` by providing the model paramete
   <TabItem value="curl">
 
 ```bash
-curl -X POST "http://0.0.0.0:8000/model/new" \
+curl -X POST "http://0.0.0.0:4000/model/new" \
      -H "accept: application/json" \
      -H "Content-Type: application/json" \
      -d '{ "model_name": "azure-gpt-turbo", "litellm_params": {"model": "azure/gpt-3.5-turbo", "api_key": "os.environ/AZURE_API_KEY", "api_base": "my-azure-api-base"} }'

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

@@ -96,7 +96,7 @@ Turn off PII masking for a given key.
 Do this by setting `permissions: {"pii": false}`, when generating a key. 
 
 ```shell 
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{
@@ -119,7 +119,7 @@ The proxy support 2 request-level PII controls:
 Set `allow_pii_controls` to true for a given key. This will allow the user to set request-level PII controls.
 
 ```bash
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer my-master-key' \
 --header 'Content-Type: application/json' \
 --data '{
@@ -136,7 +136,7 @@ from openai import OpenAI
 client = OpenAI(
     # This is the default and can be omitted
     api_key=os.environ.get("OPENAI_API_KEY"),
-        base_url="http://0.0.0.0:8000"
+        base_url="http://0.0.0.0:4000"
 )
 
 chat_completion = client.chat.completions.create(

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

@@ -21,7 +21,7 @@ Run the following command to start the litellm proxy
 ```shell
 $ litellm --model huggingface/bigcode/starcoder
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 ### Test
@@ -250,7 +250,7 @@ litellm --config your_config.yaml
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -270,7 +270,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -297,7 +297,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000", # set openai_api_base to the LiteLLM Proxy
+    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
     model = "gpt-3.5-turbo",
     temperature=0.1
 )
@@ -321,7 +321,7 @@ print(response)
 ```python
 from langchain.embeddings import OpenAIEmbeddings
 
-embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 
 text = "This is a test document."
@@ -331,7 +331,7 @@ query_result = embeddings.embed_query(text)
 print(f"SAGEMAKER EMBEDDINGS")
 print(query_result[:5])
 
-embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 text = "This is a test document."
 
@@ -340,7 +340,7 @@ query_result = embeddings.embed_query(text)
 print(f"BEDROCK EMBEDDINGS")
 print(query_result[:5])
 
-embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 text = "This is a test document."
 
@@ -407,11 +407,11 @@ services:
   litellm:
     image: ghcr.io/berriai/litellm:main
     ports:
-      - "8000:8000" # Map the container port to the host, change the host port if necessary
+      - "4000:4000" # Map the container port to the host, change the host port if necessary
     volumes:
       - ./litellm-config.yaml:/app/config.yaml # Mount the local configuration file
     # You can change the port or number of workers as per your requirements or pass any new supported CLI augument. Make sure the port passed here matches with the container port defined above in `ports` value
-    command: [ "--config", "/app/config.yaml", "--port", "8000", "--num_workers", "8" ]
+    command: [ "--config", "/app/config.yaml", "--port", "4000", "--num_workers", "8" ]
 
 # ...rest of your docker-compose config if any
 ```
@@ -429,7 +429,7 @@ Run the command `docker-compose up` or `docker compose up` as per your docker in
 > Use `-d` flag to run the container in detached mode (background) e.g. `docker compose up -d`
 
 
-Your LiteLLM container should be running now on the defined port e.g. `8000`.
+Your LiteLLM container should be running now on the defined port e.g. `4000`.
 
 
 ## Using with OpenAI compatible projects
@@ -442,7 +442,7 @@ Set `base_url` to the LiteLLM Proxy server
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -463,7 +463,7 @@ print(response)
 ```shell
 litellm --model gpt-3.5-turbo
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 #### 1. Clone the repo
@@ -474,9 +474,9 @@ git clone https://github.com/danny-avila/LibreChat.git
 
 
 #### 2. Modify Librechat's `docker-compose.yml`
-LiteLLM Proxy is running on port `8000`, set `8000` as the proxy below
+LiteLLM Proxy is running on port `4000`, set `4000` as the proxy below
 ```yaml
-OPENAI_REVERSE_PROXY=http://host.docker.internal:8000/v1/chat/completions
+OPENAI_REVERSE_PROXY=http://host.docker.internal:4000/v1/chat/completions
 ```
 
 #### 3. Save fake OpenAI key in Librechat's `.env` 
@@ -502,7 +502,7 @@ In the [config.py](https://continue.dev/docs/reference/Models/openai) set this a
       api_key="IGNORED",
       model="fake-model-name",
       context_length=2048, # customize if needed for your model
-      api_base="http://localhost:8000" # your proxy server url
+      api_base="http://localhost:4000" # your proxy server url
   ),
 ```
 
@@ -514,7 +514,7 @@ Credits [@vividfog](https://github.com/jmorganca/ollama/issues/305#issuecomment-
 ```shell
 $ pip install aider 
 
-$ aider --openai-api-base http://0.0.0.0:8000 --openai-api-key fake-key
+$ aider --openai-api-base http://0.0.0.0:4000 --openai-api-key fake-key
 ```
 </TabItem>
 <TabItem value="autogen" label="AutoGen">
@@ -528,7 +528,7 @@ from autogen import AssistantAgent, UserProxyAgent, oai
 config_list=[
     {
         "model": "my-fake-model",
-        "api_base": "http://localhost:8000",  #litellm compatible endpoint
+        "api_base": "http://localhost:4000",  #litellm compatible endpoint
         "api_type": "open_ai",
         "api_key": "NULL", # just a placeholder
     }
@@ -566,7 +566,7 @@ import guidance
 
 # set api_base to your proxy
 # set api_key to anything
-gpt4 = guidance.llms.OpenAI("gpt-4", api_base="http://0.0.0.0:8000", api_key="anything")
+gpt4 = guidance.llms.OpenAI("gpt-4", api_base="http://0.0.0.0:4000", api_key="anything")
 
 experts = guidance('''
 {{#system~}}

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

@@ -45,7 +45,7 @@ litellm_settings:
 **Set dynamically**
 
 ```bash
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "zephyr-beta",
@@ -101,7 +101,7 @@ LiteLLM Proxy supports setting a `timeout` per request
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
      --header 'Content-Type: application/json' \
      --data-raw '{
         "model": "gpt-3.5-turbo",
@@ -121,7 +121,7 @@ import openai
 
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 response = client.chat.completions.create(

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

@@ -30,7 +30,7 @@ $ litellm /path/to/config.yaml
 ```
 
 ```bash
-curl --location 'http://0.0.0.0:8000/v1/chat/completions' \
+curl --location 'http://0.0.0.0:4000/v1/chat/completions' \
 --header 'Content-Type: application/json' \
 --header 'Authorization: Bearer sk-1234' \
 --data '{

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

@@ -65,7 +65,7 @@ litellm --config proxy_config.yaml
 ```
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Authorization: Bearer sk-1234' \
     --data ' {
     "model": "gpt-3.5-turbo",

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

@@ -28,12 +28,12 @@ Follow [setup](./virtual_keys.md#setup)
 ```bash
 litellm --config /path/to/config.yaml
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 ### 2. Go to UI 
 ```bash
-http://0.0.0.0:8000/ui # <proxy_base_url>/ui
+http://0.0.0.0:4000/ui # <proxy_base_url>/ui
 ```
 
 

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

@@ -26,7 +26,7 @@ Set `extra_body={"metadata": { }}` to `metadata` you want to pass
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -92,7 +92,7 @@ print(response)
 Pass `metadata` as part of the request body
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Content-Type: application/json' \
     --data '{
     "model": "gpt-3.5-turbo",
@@ -123,7 +123,7 @@ from langchain.prompts.chat import (
 from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
-    openai_api_base="http://0.0.0.0:8000",
+    openai_api_base="http://0.0.0.0:4000",
     model = "gpt-3.5-turbo",
     temperature=0.1,
     extra_body={
@@ -195,7 +195,7 @@ from openai import OpenAI
 
 # set base_url to your proxy server
 # set api_key to send to proxy server
-client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:8000")
+client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
 
 response = client.embeddings.create(
     input=["hello from litellm"],
@@ -209,7 +209,7 @@ print(response)
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/embeddings' \
+curl --location 'http://0.0.0.0:4000/embeddings' \
   --header 'Content-Type: application/json' \
   --data ' {
   "model": "text-embedding-ada-002",
@@ -223,7 +223,7 @@ curl --location 'http://0.0.0.0:8000/embeddings' \
 ```python
 from langchain.embeddings import OpenAIEmbeddings
 
-embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 
 text = "This is a test document."
@@ -233,7 +233,7 @@ query_result = embeddings.embed_query(text)
 print(f"SAGEMAKER EMBEDDINGS")
 print(query_result[:5])
 
-embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 text = "This is a test document."
 
@@ -242,7 +242,7 @@ query_result = embeddings.embed_query(text)
 print(f"BEDROCK EMBEDDINGS")
 print(query_result[:5])
 
-embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key")
+embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:4000", openai_api_key="temp-key")
 
 text = "This is a test document."
 
@@ -296,7 +296,7 @@ from openai import OpenAI
 
 # set base_url to your proxy server
 # set api_key to send to proxy server
-client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:8000")
+client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
 
 response = client.moderations.create(
     input="hello from litellm",
@@ -310,7 +310,7 @@ print(response)
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/moderations' \
+curl --location 'http://0.0.0.0:4000/moderations' \
     --header 'Content-Type: application/json' \
     --header 'Authorization: Bearer sk-1234' \
     --data '{"input": "Sample text goes here", "model": "text-moderation-stable"}'
@@ -421,7 +421,7 @@ user_config = {
 import openai
 client = openai.OpenAI(
     api_key="sk-1234",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # send request to `user-azure-instance`
@@ -489,7 +489,7 @@ const { OpenAI } = require('openai');
 
 const openai = new OpenAI({
   apiKey: "sk-1234",
-  baseURL: "http://0.0.0.0:8000"
+  baseURL: "http://0.0.0.0:4000"
 });
 
 async function main() {
@@ -516,7 +516,7 @@ Here's how to do it:
 import openai
 client = openai.OpenAI(
     api_key="sk-1234",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -541,7 +541,7 @@ Pass in the litellm_params (E.g. api_key, api_base, etc.) via the `extra_body` p
 import openai
 client = openai.OpenAI(
     api_key="sk-1234",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -571,7 +571,7 @@ const { OpenAI } = require('openai');
 
 const openai = new OpenAI({
   apiKey: "sk-1234",
-  baseURL: "http://0.0.0.0:8000"
+  baseURL: "http://0.0.0.0:4000"
 });
 
 async function main() {

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

@@ -44,7 +44,7 @@ litellm /path/to/config.yaml
 **Step 3. Send test call**
 
 ```bash
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Autherization: Bearer sk-1234' \
     --header 'Content-Type: application/json' \
     --data '{
@@ -72,7 +72,7 @@ By default the `max_budget` is set to `null` and is not checked for keys
 
 #### **Add budgets to users**
 ```shell 
-curl --location 'http://localhost:8000/user/new' \
+curl --location 'http://localhost:4000/user/new' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{"models": ["azure-models"], "max_budget": 0, "user_id": "krrish3@berri.ai"}' 
@@ -96,7 +96,7 @@ curl --location 'http://localhost:8000/user/new' \
 `budget_duration`: Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
 
 ```
-curl 'http://0.0.0.0:8000/user/new' \
+curl 'http://0.0.0.0:4000/user/new' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -113,7 +113,7 @@ Now you can just call `/key/generate` with that user_id (i.e. krrish3@berri.ai)
 - **Spend Tracking**: spend for this key will update krrish3@berri.ai's spend as well
 
 ```bash
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data '{"models": ["azure-models"], "user_id": "krrish3@berri.ai"}'
@@ -127,7 +127,7 @@ You can:
 
 #### **Add budgets to users**
 ```shell 
-curl --location 'http://localhost:8000/team/new' \
+curl --location 'http://localhost:4000/team/new' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -238,7 +238,7 @@ By default the `max_budget` is set to `null` and is not checked for keys
 #### **Add budgets to keys**
 
 ```bash
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -250,7 +250,7 @@ curl 'http://0.0.0.0:8000/key/generate' \
 Example Request to `/chat/completions` when key has crossed budget
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer <generated-key>' \
   --data ' {
@@ -278,7 +278,7 @@ Expected Response from `/chat/completions` when key has crossed budget
 `budget_duration`: Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
 
 ```
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -310,7 +310,7 @@ By default the `model_max_budget` is set to `{}` and is not checked for keys
 #### **Add model specific budgets to keys**
 
 ```bash
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -335,7 +335,7 @@ Use `/user/new`, to persist rate limits across multiple keys.
 
 
 ```shell
-curl --location 'http://0.0.0.0:8000/user/new' \
+curl --location 'http://0.0.0.0:4000/user/new' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{"user_id": "krrish@berri.ai", "max_parallel_requests": 10, "tpm_limit": 20, "rpm_limit": 4}' 
@@ -359,7 +359,7 @@ curl --location 'http://0.0.0.0:8000/user/new' \
 Use `/key/generate`, if you want them for just that key.
 
 ```shell
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{"max_parallel_requests": 10, "tpm_limit": 20, "rpm_limit": 4}' 
@@ -401,7 +401,7 @@ model_list:
 **Step 2. Create key with access group**
 
 ```bash
-curl --location 'http://localhost:8000/user/new' \
+curl --location 'http://localhost:4000/user/new' \
 -H 'Authorization: Bearer <your-master-key>' \
 -H 'Content-Type: application/json' \
 -d '{"models": ["beta-models"], # 👈 Model Access Group
@@ -414,7 +414,7 @@ curl --location 'http://localhost:8000/user/new' \
 Just include user_id in the `/key/generate` request.
 
 ```bash
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data '{"models": ["azure-models"], "user_id": "krrish@berri.ai"}'

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

@@ -59,7 +59,7 @@ litellm --config /path/to/config.yaml
 **Step 3: Generate temporary keys**
 
 ```shell 
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{"models": ["gpt-3.5-turbo", "gpt-4", "claude-2"], "duration": "20m","metadata": {"user": "ishaan@berri.ai"}}'
@@ -70,7 +70,7 @@ curl 'http://0.0.0.0:8000/key/generate' \
 
 ### Request
 ```shell
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -105,7 +105,7 @@ Request Params:
 ```python
 {
     "key": "sk-kdEXbIqZRwEeEiHwdg7sFA", # Bearer token
-    "expires": "2023-11-19T01:38:25.838000+00:00" # datetime object
+    "expires": "2023-11-19T01:38:25.834000+00:00" # datetime object
     "key_name": "sk-...7sFA" # abbreviated key string, ONLY stored in db if `allow_user_auth: true` set - [see](./ui.md)
     ...
 }
@@ -147,7 +147,7 @@ model_list:
 **Step 2: Generate a user key - enabling them access to specific models, custom model aliases, etc.**
 
 ```bash
-curl -X POST "https://0.0.0.0:8000/key/generate" \
+curl -X POST "https://0.0.0.0:4000/key/generate" \
 -H "Authorization: Bearer <your-master-key>" \
 -H "Content-Type: application/json" \
 -d '{
@@ -182,7 +182,7 @@ model_list:
 **Step 2. Create key with access group**
 
 ```bash
-curl --location 'http://localhost:8000/key/generate' \
+curl --location 'http://localhost:4000/key/generate' \
 -H 'Authorization: Bearer <your-master-key>' \
 -H 'Content-Type: application/json' \
 -d '{"models": ["beta-models"], # 👈 Model Access Group
@@ -194,7 +194,7 @@ curl --location 'http://localhost:8000/key/generate' \
 
 ### Request
 ```shell
-curl -X GET "http://0.0.0.0:8000/key/info?key=sk-02Wr4IAlN3NvPXvL5JVvDA" \
+curl -X GET "http://0.0.0.0:4000/key/info?key=sk-02Wr4IAlN3NvPXvL5JVvDA" \
 -H "Authorization: Bearer sk-1234"
 ```
 
@@ -228,7 +228,7 @@ Request Params:
 
 ### Request
 ```shell
-curl 'http://0.0.0.0:8000/key/update' \
+curl 'http://0.0.0.0:4000/key/update' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -266,7 +266,7 @@ Request Params:
 
 ### Request
 ```shell
-curl 'http://0.0.0.0:8000/key/delete' \
+curl 'http://0.0.0.0:4000/key/delete' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -500,7 +500,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 Set `max_budget` in (USD $) param in the `key/generate` request. By default the `max_budget` is set to `null` and is not checked for keys
 
 ```shell
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{
@@ -517,7 +517,7 @@ curl 'http://0.0.0.0:8000/key/generate' \
 Example Request to `/chat/completions` when key has crossed budget
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer sk-ULl_IKCVFy2EZRzQB16RUA' \
   --data ' {
@@ -545,10 +545,10 @@ Expected Response from `/chat/completions` when key has crossed budget
 
 LiteLLM exposes a `/user/new` endpoint to create budgets for users, that persist across multiple keys. 
 
-This is documented in the swagger (live on your server root endpoint - e.g. `http://0.0.0.0:8000/`). Here's an example request. 
+This is documented in the swagger (live on your server root endpoint - e.g. `http://0.0.0.0:4000/`). Here's an example request. 
 
 ```shell 
-curl --location 'http://localhost:8000/user/new' \
+curl --location 'http://localhost:4000/user/new' \
 --header 'Authorization: Bearer <your-master-key>' \
 --header 'Content-Type: application/json' \
 --data-raw '{"models": ["azure-models"], "max_budget": 0, "user_id": "krrish3@berri.ai"}' 
@@ -571,7 +571,7 @@ The request is a normal `/key/generate` request body + a `max_budget` field.
 You can get spend for a key by using the `/key/info` endpoint. 
 
 ```bash
-curl 'http://0.0.0.0:8000/key/info?key=<user-key>' \
+curl 'http://0.0.0.0:4000/key/info?key=<user-key>' \
      -X GET \
      -H 'Authorization: Bearer <your-master-key>'
 ```
@@ -771,7 +771,7 @@ general_settings:
 #### Step 3. Generate Key
 
 ```bash
-curl --location 'http://0.0.0.0:8000/key/generate' \
+curl --location 'http://0.0.0.0:4000/key/generate' \
 --header 'Authorization: Bearer sk-1234' \
 --header 'Content-Type: application/json' \
 --data '{"models": ["azure-models"], "aliases": {"mistral-7b": "gpt-3.5-turbo"}, "duration": null}'

docs/my-website/docs/simple_proxy_old_doc.md

@@ -22,7 +22,7 @@ $ pip install 'litellm[proxy]'
 ```shell
 $ litellm --model huggingface/bigcode/starcoder
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 ### Test
@@ -39,7 +39,7 @@ This will now automatically route any requests for gpt-3.5-turbo to bigcode star
 <TabItem value="Curl" label="Curl Request">
 
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -59,7 +59,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -246,7 +246,7 @@ Set `base_url` to the LiteLLM Proxy server
 import openai
 client = openai.OpenAI(
     api_key="anything",
-    base_url="http://0.0.0.0:8000"
+    base_url="http://0.0.0.0:4000"
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
@@ -267,7 +267,7 @@ print(response)
 ```shell
 litellm --model gpt-3.5-turbo
 
-#INFO: Proxy running on http://0.0.0.0:8000
+#INFO: Proxy running on http://0.0.0.0:4000
 ```
 
 #### 1. Clone the repo
@@ -278,9 +278,9 @@ git clone https://github.com/danny-avila/LibreChat.git
 
 
 #### 2. Modify Librechat's `docker-compose.yml`
-LiteLLM Proxy is running on port `8000`, set `8000` as the proxy below
+LiteLLM Proxy is running on port `4000`, set `4000` as the proxy below
 ```yaml
-OPENAI_REVERSE_PROXY=http://host.docker.internal:8000/v1/chat/completions
+OPENAI_REVERSE_PROXY=http://host.docker.internal:4000/v1/chat/completions
 ```
 
 #### 3. Save fake OpenAI key in Librechat's `.env` 
@@ -306,7 +306,7 @@ In the [config.py](https://continue.dev/docs/reference/Models/openai) set this a
       api_key="IGNORED",
       model="fake-model-name",
       context_length=2048, # customize if needed for your model
-      api_base="http://localhost:8000" # your proxy server url
+      api_base="http://localhost:4000" # your proxy server url
   ),
 ```
 
@@ -318,7 +318,7 @@ Credits [@vividfog](https://github.com/jmorganca/ollama/issues/305#issuecomment-
 ```shell
 $ pip install aider 
 
-$ aider --openai-api-base http://0.0.0.0:8000 --openai-api-key fake-key
+$ aider --openai-api-base http://0.0.0.0:4000 --openai-api-key fake-key
 ```
 </TabItem>
 <TabItem value="autogen" label="AutoGen">
@@ -332,7 +332,7 @@ from autogen import AssistantAgent, UserProxyAgent, oai
 config_list=[
     {
         "model": "my-fake-model",
-        "api_base": "http://localhost:8000",  #litellm compatible endpoint
+        "api_base": "http://localhost:4000",  #litellm compatible endpoint
         "api_type": "open_ai",
         "api_key": "NULL", # just a placeholder
     }
@@ -370,7 +370,7 @@ import guidance
 
 # set api_base to your proxy
 # set api_key to anything
-gpt4 = guidance.llms.OpenAI("gpt-4", api_base="http://0.0.0.0:8000", api_key="anything")
+gpt4 = guidance.llms.OpenAI("gpt-4", api_base="http://0.0.0.0:4000", api_key="anything")
 
 experts = guidance('''
 {{#system~}}
@@ -479,7 +479,7 @@ $ litellm --config /path/to/config.yaml
 #### Step 3: Use proxy
 Curl Command
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "zephyr-alpha",
@@ -529,7 +529,7 @@ $ litellm --config /path/to/config.yaml
 #### Step 3: Use proxy
 Curl Command
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "gpt-3.5-turbo",
@@ -586,7 +586,7 @@ litellm_settings:
 **Set dynamically**
 
 ```bash
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
       "model": "zephyr-beta",
@@ -615,7 +615,7 @@ model_list:
   - model_name: custom_embedding_model
     litellm_params:
       model: openai/custom_embedding  # the `openai/` prefix tells litellm it's openai compatible
-      api_base: http://0.0.0.0:8000/
+      api_base: http://0.0.0.0:4000/
   - model_name: custom_embedding_model
     litellm_params:
       model: openai/custom_embedding  # the `openai/` prefix tells litellm it's openai compatible
@@ -665,7 +665,7 @@ litellm --config /path/to/config.yaml
 **Step 3: Generate temporary keys**
 
 ```shell 
-curl 'http://0.0.0.0:8000/key/generate' \
+curl 'http://0.0.0.0:4000/key/generate' \
 --h 'Authorization: Bearer sk-1234' \
 --d '{"models": ["gpt-3.5-turbo", "gpt-4", "claude-2"], "duration": "20m"}'
 ```
@@ -719,7 +719,7 @@ model_list:
 **Step 2: Generate a user key - enabling them access to specific models, custom model aliases, etc.**
 
 ```bash
-curl -X POST "https://0.0.0.0:8000/key/generate" \
+curl -X POST "https://0.0.0.0:4000/key/generate" \
 -H "Authorization: Bearer sk-1234" \
 -H "Content-Type: application/json" \
 -d '{
@@ -737,7 +737,7 @@ curl -X POST "https://0.0.0.0:8000/key/generate" \
 You can get spend for a key by using the `/key/info` endpoint. 
 
 ```bash
-curl 'http://0.0.0.0:8000/key/info?key=<user-key>' \
+curl 'http://0.0.0.0:4000/key/info?key=<user-key>' \
      -X GET \
      -H 'Authorization: Bearer <your-master-key>'
 ```
@@ -868,7 +868,7 @@ $ litellm --config /path/to/config.yaml
 #### Using Caching 
 Send the same request twice:
 ```shell
-curl http://0.0.0.0:8000/v1/chat/completions \
+curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -876,7 +876,7 @@ curl http://0.0.0.0:8000/v1/chat/completions \
      "temperature": 0.7
    }'
 
-curl http://0.0.0.0:8000/v1/chat/completions \
+curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -889,7 +889,7 @@ curl http://0.0.0.0:8000/v1/chat/completions \
 Caching can be switched on/off per `/chat/completions` request
 - Caching **on** for completion - pass `caching=True`:
   ```shell
-  curl http://0.0.0.0:8000/v1/chat/completions \
+  curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -900,7 +900,7 @@ Caching can be switched on/off per `/chat/completions` request
   ```
 - Caching **off** for completion - pass `caching=False`:
   ```shell
-  curl http://0.0.0.0:8000/v1/chat/completions \
+  curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
      "model": "gpt-3.5-turbo",
@@ -963,10 +963,10 @@ https://api.openai.com/v1/chat/completions \
 Use this to health check all LLMs defined in your config.yaml
 #### Request
 ```shell
-curl --location 'http://0.0.0.0:8000/health'
+curl --location 'http://0.0.0.0:4000/health'
 ```
 
-You can also run `litellm -health` it makes a `get` request to `http://0.0.0.0:8000/health` for you
+You can also run `litellm -health` it makes a `get` request to `http://0.0.0.0:4000/health` for you
 ```
 litellm --health
 ```
@@ -1087,7 +1087,7 @@ litellm -config config.yaml
 
 #### Run a test request to Proxy
 ```shell
-curl --location 'http://0.0.0.0:8000/chat/completions' \
+curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Authorization: Bearer sk-1244' \
     --data ' {
     "model": "gpt-3.5-turbo",
@@ -1213,7 +1213,7 @@ LiteLLM proxy adds **0.00325 seconds** latency as compared to using the Raw Open
      ```
 
 #### --port
-   - **Default:** `8000`
+   - **Default:** `4000`
    - The port to bind the server to.
    - **Usage:** 
      ```shell

litellm/proxy/proxy_cli.py

@@ -61,7 +61,7 @@ def is_port_in_use(port):
 @click.option(
     "--host", default="0.0.0.0", help="Host for the server to listen on.", envvar="HOST"
 )
-@click.option("--port", default=8000, help="Port to bind the server to.", envvar="PORT")
+@click.option("--port", default=4000, help="Port to bind the server to.", envvar="PORT")
 @click.option(
     "--num_workers",
     default=default_num_workers,
@@ -273,7 +273,7 @@ def run_server(
                 ],
             }
 
-            response = requests.post("http://0.0.0.0:8000/queue/request", json=data)
+            response = requests.post("http://0.0.0.0:4000/queue/request", json=data)
 
             response = response.json()
 
@@ -507,7 +507,7 @@ def run_server(
                 print(
                     f"Unable to connect to DB. DATABASE_URL found in environment, but prisma package not found."
                 )
-        if port == 8000 and is_port_in_use(port):
+        if port == 4000 and is_port_in_use(port):
             port = random.randint(1024, 49152)
 
         from litellm.proxy.proxy_server import app

litellm/router.py

@@ -246,7 +246,7 @@ class Router:
             "122999-2828282-277:
             {
                 "model": "gpt-3",
-                "api_base": "http://localhost:8000",
+                "api_base": "http://localhost:4000",
                 "num_requests": 20,
                 "avg_latency": 0.001,
                 "num_failures": 0,