From 52bf7500bb93da8df0e63a34a8a55db8ce3e0407 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Mon, 8 Jun 2026 15:03:31 -0700 Subject: [PATCH 1/4] docs: rename litellm-proxy CLI command to lite The proxy CLI console script was renamed from litellm-proxy to lite (BerriAI/litellm#29850), so the management CLI and CLI authentication pages now teach `lite ...` instead of `litellm-proxy ...`, including the "Installed 2 executables" hint. Env vars (LITELLM_PROXY_URL, LITELLM_PROXY_API_KEY), the litellm[proxy] install, and historical release notes are intentionally left unchanged. --- docs/proxy/cli_sso.md | 12 +++---- docs/proxy/management_cli.md | 62 ++++++++++++++++++------------------ 2 files changed, 37 insertions(+), 37 deletions(-) diff --git a/docs/proxy/cli_sso.md b/docs/proxy/cli_sso.md index 7598edeba..ca9f316db 100644 --- a/docs/proxy/cli_sso.md +++ b/docs/proxy/cli_sso.md @@ -59,7 +59,7 @@ When `EXPERIMENTAL_UI_LOGIN` is enabled, the **browser UI login** session uses a :::tip You can check your current token's age and expiration status using: ```bash -litellm-proxy whoami +lite whoami ``` ::: @@ -113,13 +113,13 @@ Example poll response (after SSO completes): ```shell ... - Installed 2 executables: litellm, litellm-proxy + Installed 2 executables: litellm, lite ``` - and now you can use the tool by just typing `litellm-proxy` in your terminal: + and now you can use the tool by just typing `lite` in your terminal: ```shell - litellm-proxy + lite ``` 2. **Set up environment variables** @@ -135,7 +135,7 @@ Example poll response (after SSO completes): 3. **Login** ```shell - litellm-proxy login + lite login ``` This will open a browser window to authenticate. If you have connected LiteLLM Proxy to your SSO provider, you should be able to login with your SSO credentials. Once logged in, you can use the CLI to make requests to the LiteLLM Gateway. @@ -143,7 +143,7 @@ Example poll response (after SSO completes): 4. **Make a test request to view models** ```shell - litellm-proxy models list + lite models list ``` This will list all the models available to you. \ No newline at end of file diff --git a/docs/proxy/management_cli.md b/docs/proxy/management_cli.md index 23a568421..998d51474 100644 --- a/docs/proxy/management_cli.md +++ b/docs/proxy/management_cli.md @@ -1,6 +1,6 @@ # LiteLLM Proxy CLI -The `litellm-proxy` CLI is a command-line tool for managing your LiteLLM proxy +The `lite` 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. @@ -27,13 +27,13 @@ and more, as well as making chat and HTTP requests to the proxy server. ```shell ... - Installed 2 executables: litellm, litellm-proxy + Installed 2 executables: litellm, lite ``` - and now you can use the tool by just typing `litellm-proxy` in your terminal: + and now you can use the tool by just typing `lite` in your terminal: ```shell - litellm-proxy + lite ``` 2. **Set up environment variables** @@ -48,7 +48,7 @@ and more, as well as making chat and HTTP requests to the proxy server. 3. **Make your first request (list models)** ```bash - litellm-proxy models list + lite models list ``` If the CLI is set up correctly, you should see a list of available models or a table output. @@ -99,7 +99,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 2. **Login** ```bash - litellm-proxy login + lite 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. @@ -107,7 +107,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 3. **Test your authentication** ```bash - litellm-proxy models list + lite models list ``` This will list all the models available to you. @@ -120,12 +120,12 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy models list - litellm-proxy models add gpt-4 \ + lite models list + lite models add gpt-4 \ --param api_key=sk-123 \ --param max_tokens=2048 - litellm-proxy models update -p temperature=0.7 - litellm-proxy models delete + lite models update -p temperature=0.7 + lite models delete ``` [API used (OpenAPI)](https://litellm-api.up.railway.app/#/model%20management) @@ -136,12 +136,12 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy credentials list - litellm-proxy credentials create azure-prod \ + lite credentials list + lite 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 + lite credentials get azure-cred + lite credentials delete azure-cred ``` [API used (OpenAPI)](https://litellm-api.up.railway.app/#/credential%20management) @@ -152,14 +152,14 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy keys list - litellm-proxy keys generate \ + lite keys list + lite 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 + lite keys info --key sk-key1 + lite keys delete --keys sk-key1,sk-key2 --key-aliases alias1,alias2 ``` [API used (OpenAPI)](https://litellm-api.up.railway.app/#/key%20management) @@ -170,15 +170,15 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy users list - litellm-proxy users create \ + lite users list + lite users create \ --email=user@example.com \ --role=internal_user \ --alias="Alice" \ --team=team1 \ --max-budget=100.0 - litellm-proxy users get --id - litellm-proxy users delete + lite users get --id + lite users delete ``` [API used (OpenAPI)](https://litellm-api.up.railway.app/#/Internal%20User%20management) @@ -189,7 +189,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy chat completions gpt-4 -m "user:Hello, how are you?" + lite chat completions gpt-4 -m "user:Hello, how are you?" ``` [API used (OpenAPI)](https://litellm-api.up.railway.app/#/chat%2Fcompletions) @@ -200,7 +200,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml - Example: ```bash - litellm-proxy http request \ + lite http request \ POST /chat/completions \ --json '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}]}' ``` @@ -217,13 +217,13 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 1. **List all models:** ```bash - litellm-proxy models list + lite models list ``` 2. **Add a new model:** ```bash - litellm-proxy models add gpt-4 \ + lite models add gpt-4 \ --param api_key=sk-123 \ --param max_tokens=2048 ``` @@ -231,7 +231,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 3. **Create a credential:** ```bash - litellm-proxy credentials create azure-prod \ + lite credentials create azure-prod \ --info='{"custom_llm_provider": "azure"}' \ --values='{"api_key": "sk-123", "api_base": "https://prod.azure.openai.com"}' ``` @@ -239,7 +239,7 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 4. **Generate an API key:** ```bash - litellm-proxy keys generate \ + lite keys generate \ --models=gpt-4 \ --spend=100 \ --duration=24h \ @@ -249,14 +249,14 @@ EXPERIMENTAL_UI_LOGIN="True" litellm --config config.yaml 5. **Chat completion:** ```bash - litellm-proxy chat completions gpt-4 \ + lite chat completions gpt-4 \ -m "user:Write a story" ``` 6. **Custom HTTP request:** ```bash - litellm-proxy http request \ + lite http request \ POST /chat/completions \ --json '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}]}' ``` From 30a081afc4f2e004fd9bb8edc957dad43e364d78 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Mon, 8 Jun 2026 18:07:40 -0700 Subject: [PATCH 2/4] docs: add the one-line curl installer for the lite CLI Document the curl | sh installer alongside `uv tool install` in the management CLI and CLI authentication install steps, since it needs only curl and provisions a Python runtime when one isn't present. --- docs/proxy/cli_sso.md | 11 +++++------ docs/proxy/management_cli.md | 11 +++++------ 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/docs/proxy/cli_sso.md b/docs/proxy/cli_sso.md index ca9f316db..15a5dc1ae 100644 --- a/docs/proxy/cli_sso.md +++ b/docs/proxy/cli_sso.md @@ -103,20 +103,19 @@ Example poll response (after SSO completes): 1. **Install the CLI** - If you have [uv](https://github.com/astral-sh/uv) installed, you can try this: + The one-line installer needs only `curl`; it installs a Python runtime for you if you don't already have one: ```shell - uv tool install 'litellm[proxy]' + curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh ``` - If that works, you'll see something like this: + Or, if you already have [uv](https://github.com/astral-sh/uv): ```shell - ... - Installed 2 executables: litellm, lite + uv tool install 'litellm[proxy]' ``` - and now you can use the tool by just typing `lite` in your terminal: + Either way the `lite` command is now available, so you can use the tool by just typing `lite` in your terminal: ```shell lite diff --git a/docs/proxy/management_cli.md b/docs/proxy/management_cli.md index 998d51474..3d7731d39 100644 --- a/docs/proxy/management_cli.md +++ b/docs/proxy/management_cli.md @@ -17,20 +17,19 @@ and more, as well as making chat and HTTP requests to the proxy server. 1. **Install the CLI** - If you have [uv](https://github.com/astral-sh/uv) installed, you can try this: + The one-line installer needs only `curl`; it installs a Python runtime for you if you don't already have one: ```shell - uv tool install 'litellm[proxy]' + curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh ``` - If that works, you'll see something like this: + Or, if you already have [uv](https://github.com/astral-sh/uv): ```shell - ... - Installed 2 executables: litellm, lite + uv tool install 'litellm[proxy]' ``` - and now you can use the tool by just typing `lite` in your terminal: + Either way the `lite` command is now available, so you can use the tool by just typing `lite` in your terminal: ```shell lite From a74b55de05104b8e4b242a9e9c7bb1144e99b9fc Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Mon, 8 Jun 2026 18:33:11 -0700 Subject: [PATCH 3/4] docs(cli): clarify the curl installer bootstraps uv and installs the full proxy package --- docs/proxy/cli_sso.md | 6 +++--- docs/proxy/management_cli.md | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/proxy/cli_sso.md b/docs/proxy/cli_sso.md index 15a5dc1ae..6355c548d 100644 --- a/docs/proxy/cli_sso.md +++ b/docs/proxy/cli_sso.md @@ -103,19 +103,19 @@ Example poll response (after SSO completes): 1. **Install the CLI** - The one-line installer needs only `curl`; it installs a Python runtime for you if you don't already have one: + The one-line installer needs only `curl`. It bootstraps everything else: it installs [uv](https://github.com/astral-sh/uv) when it's missing, then uses uv to provision a Python runtime if you don't already have one: ```shell curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh ``` - Or, if you already have [uv](https://github.com/astral-sh/uv): + Already have uv and prefer to drive it yourself? Install the package directly instead: ```shell uv tool install 'litellm[proxy]' ``` - Either way the `lite` command is now available, so you can use the tool by just typing `lite` in your terminal: + Either way you get the full `litellm[proxy]` package: the proxy server plus the `lite` management CLI. The `lite` command is now available, so start by typing it in your terminal: ```shell lite diff --git a/docs/proxy/management_cli.md b/docs/proxy/management_cli.md index 3d7731d39..af5a3a41a 100644 --- a/docs/proxy/management_cli.md +++ b/docs/proxy/management_cli.md @@ -17,19 +17,19 @@ and more, as well as making chat and HTTP requests to the proxy server. 1. **Install the CLI** - The one-line installer needs only `curl`; it installs a Python runtime for you if you don't already have one: + The one-line installer needs only `curl`. It bootstraps everything else: it installs [uv](https://github.com/astral-sh/uv) when it's missing, then uses uv to provision a Python runtime if you don't already have one: ```shell curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh ``` - Or, if you already have [uv](https://github.com/astral-sh/uv): + Already have uv and prefer to drive it yourself? Install the package directly instead: ```shell uv tool install 'litellm[proxy]' ``` - Either way the `lite` command is now available, so you can use the tool by just typing `lite` in your terminal: + Either way you get the full `litellm[proxy]` package: the proxy server plus the `lite` management CLI. The `lite` command is now available, so start by typing it in your terminal: ```shell lite From 9f47ae2470fdddd2327aed7bc667d4b369fd7c96 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Mon, 8 Jun 2026 19:21:50 -0700 Subject: [PATCH 4/4] docs(cli): point install at the thin litellm[cli] client Switch the management CLI Quick Start (and SSO login steps) from the full litellm[proxy] install to the thin lite client: scripts/install-cli.sh, a Homebrew option, and uv tool install 'litellm[cli]'. Note that proxy operators already have lite bundled with litellm[proxy]. --- docs/proxy/cli_sso.md | 16 +++++++++++----- docs/proxy/management_cli.md | 16 +++++++++++----- 2 files changed, 22 insertions(+), 10 deletions(-) diff --git a/docs/proxy/cli_sso.md b/docs/proxy/cli_sso.md index 6355c548d..f72982114 100644 --- a/docs/proxy/cli_sso.md +++ b/docs/proxy/cli_sso.md @@ -103,19 +103,25 @@ Example poll response (after SSO completes): 1. **Install the CLI** - The one-line installer needs only `curl`. It bootstraps everything else: it installs [uv](https://github.com/astral-sh/uv) when it's missing, then uses uv to provision a Python runtime if you don't already have one: + The `lite` client is a thin laptop install: it points at a LiteLLM proxy and runs your coding agents through it, with none of the proxy server runtime pulled in. The one-line installer needs only `curl`; it bootstraps [uv](https://github.com/astral-sh/uv) when it's missing and lets uv provision a compatible Python for you: ```shell - curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh + curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install-cli.sh | sh ``` - Already have uv and prefer to drive it yourself? Install the package directly instead: + On macOS you can install it with Homebrew instead: ```shell - uv tool install 'litellm[proxy]' + brew install BerriAI/litellm/lite ``` - Either way you get the full `litellm[proxy]` package: the proxy server plus the `lite` management CLI. The `lite` command is now available, so start by typing it in your terminal: + Already have uv and prefer to drive it yourself? Install the package directly: + + ```shell + uv tool install 'litellm[cli]' + ``` + + Any of these gives you the `lite` command; if you already run a proxy server from `litellm[proxy]`, it ships there too. Start by typing it in your terminal: ```shell lite diff --git a/docs/proxy/management_cli.md b/docs/proxy/management_cli.md index af5a3a41a..046588062 100644 --- a/docs/proxy/management_cli.md +++ b/docs/proxy/management_cli.md @@ -17,19 +17,25 @@ and more, as well as making chat and HTTP requests to the proxy server. 1. **Install the CLI** - The one-line installer needs only `curl`. It bootstraps everything else: it installs [uv](https://github.com/astral-sh/uv) when it's missing, then uses uv to provision a Python runtime if you don't already have one: + The `lite` client is a thin laptop install: it points at a LiteLLM proxy and runs your coding agents through it, with none of the proxy server runtime pulled in. The one-line installer needs only `curl`; it bootstraps [uv](https://github.com/astral-sh/uv) when it's missing and lets uv provision a compatible Python for you: ```shell - curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh + curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install-cli.sh | sh ``` - Already have uv and prefer to drive it yourself? Install the package directly instead: + On macOS you can install it with Homebrew instead: ```shell - uv tool install 'litellm[proxy]' + brew install BerriAI/litellm/lite ``` - Either way you get the full `litellm[proxy]` package: the proxy server plus the `lite` management CLI. The `lite` command is now available, so start by typing it in your terminal: + Already have uv and prefer to drive it yourself? Install the package directly: + + ```shell + uv tool install 'litellm[cli]' + ``` + + Any of these gives you the `lite` command; if you already run a proxy server from `litellm[proxy]`, it ships there too. Start by typing it in your terminal: ```shell lite