litellm/docs/my-website/docs/proxy/management_cli.md

LiteLLM Proxy CLI

The litellm-proxy CLI is a command-line tool for managing your LiteLLM proxy server. It provides commands for managing models, credentials, API keys, users, and more, as well as making chat and HTTP requests to the proxy server.

Feature	What you can do
Models Management	List, add, update, and delete models
Credentials Management	Manage provider credentials
Keys Management	Generate, list, and delete API keys
User Management	Create, list, and delete users
Chat Completions	Run chat completions
HTTP Requests	Make custom HTTP requests to the proxy server

Quick Start

1. Install the CLI

   If you have uv installed, you can try this:

   uv tool install 'litellm[proxy]'
   

   If that works, you'll see something like this:

   ...
   Installed 2 executables: litellm, litellm-proxy
   

   and now you can use the tool by just typing litellm-proxy in your terminal:

   litellm-proxy
   

2. Set up environment variables

   export LITELLM_PROXY_URL=http://localhost:4000
   export LITELLM_PROXY_API_KEY=sk-your-key
   

   (Replace with your actual proxy URL and API key)

3. Make your first request (list models)

   litellm-proxy models list
   

   If the CLI is set up correctly, you should see a list of available models or a table output.

4. Troubleshooting

   • If you see an error, check your environment variables and proxy server status.

Authentication using CLI

You can use the CLI to authenticate to the LiteLLM Gateway. This is great if you're trying to give a large number of developers self-serve access to the LiteLLM Gateway.

:::info

For an indepth guide, see CLI Authentication.

:::

1. Set up the proxy URL

   export LITELLM_PROXY_URL=http://localhost:4000
   

   (Replace with your actual proxy URL)

2. Login

   litellm-proxy login
   

   This will open a browser window to authenticate. If you have connected LiteLLM Proxy to your SSO provider, you can login with your SSO credentials. Once logged in, you can use the CLI to make requests to the LiteLLM Gateway.

3. Test your authentication

   litellm-proxy models list
   

   This will list all the models available to you.

Main Commands

Models Management

• List, add, update, get, and delete models on the proxy.

• Example:

  litellm-proxy models list
  litellm-proxy models add gpt-4 \
    --param api_key=sk-123 \
    --param max_tokens=2048
  litellm-proxy models update <model-id> -p temperature=0.7
  litellm-proxy models delete <model-id>
  

  API used (OpenAPI)

Credentials Management

• List, create, get, and delete credentials for LLM providers.

• Example:

  litellm-proxy credentials list
  litellm-proxy credentials create azure-prod \
    --info='{"custom_llm_provider": "azure"}' \
    --values='{"api_key": "sk-123", "api_base": "https://prod.azure.openai.com"}'
  litellm-proxy credentials get azure-cred
  litellm-proxy credentials delete azure-cred
  

  API used (OpenAPI)

Keys Management

• List, generate, get info, and delete API keys.

• Example:

  litellm-proxy keys list
  litellm-proxy keys generate \
    --models=gpt-4 \
    --spend=100 \
    --duration=24h \
    --key-alias=my-key
  litellm-proxy keys info --key sk-key1
  litellm-proxy keys delete --keys sk-key1,sk-key2 --key-aliases alias1,alias2
  

  API used (OpenAPI)

User Management

• List, create, get info, and delete users.

• Example:

  litellm-proxy users list
  litellm-proxy users create \
    --email=user@example.com \
    --role=internal_user \
    --alias="Alice" \
    --team=team1 \
    --max-budget=100.0
  litellm-proxy users get --id <user-id>
  litellm-proxy users delete <user-id>
  

  API used (OpenAPI)

Chat Completions

• Ask for chat completions from the proxy server.

• Example:

  litellm-proxy chat completions gpt-4 -m "user:Hello, how are you?"
  

  API used (OpenAPI)

General HTTP Requests

• Make direct HTTP requests to the proxy server.

• Example:

  litellm-proxy http request \
    POST /chat/completions \
    --json '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}]}'
  

  All APIs (OpenAPI)

Environment Variables

• LITELLM_PROXY_URL: Base URL of the proxy server
• LITELLM_PROXY_API_KEY: API key for authentication

Examples

1. List all models:

   litellm-proxy models list
   

2. Add a new model:

   litellm-proxy models add gpt-4 \
     --param api_key=sk-123 \
     --param max_tokens=2048
   

3. Create a credential:

   litellm-proxy credentials create azure-prod \
     --info='{"custom_llm_provider": "azure"}' \
     --values='{"api_key": "sk-123", "api_base": "https://prod.azure.openai.com"}'
   

4. Generate an API key:

   litellm-proxy keys generate \
     --models=gpt-4 \
     --spend=100 \
     --duration=24h \
     --key-alias=my-key
   

5. Chat completion:

   litellm-proxy chat completions gpt-4 \
     -m "user:Write a story"
   

6. Custom HTTP request:

   litellm-proxy http request \
     POST /chat/completions \
     --json '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}]}'
   

Error Handling

The CLI will display error messages for:

• Server not accessible
• Authentication failures
• Invalid parameters or JSON
• Nonexistent models/credentials
• Any other operation failures

Use the --debug flag for detailed debugging output.

For full command reference and advanced usage, see the CLI README.