[Staging] - Ishaan March 17th

CLAUDE.md

@@ -140,6 +140,11 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 - **Check index coverage.** For new or modified queries, check `schema.prisma` for a supporting index. Prefer extending an existing index (e.g. `@@index([a])` → `@@index([a, b])`) over adding a new one, unless it's a `@@unique`. Only add indexes for large/frequent queries.
 - **Keep schema files in sync.** Apply schema changes to all `schema.prisma` copies (`schema.prisma`, `litellm/proxy/`, `litellm-proxy-extras/`, `litellm-js/spend-logs/` for SpendLogs) with a migration under `litellm-proxy-extras/litellm_proxy_extras/migrations/`.
 
+### Setup Wizard (`litellm/setup_wizard.py`)
+- The wizard is implemented as a single `SetupWizard` class with `@staticmethod` methods — keep it that way. No module-level functions except `run_setup_wizard()` (the public entrypoint) and pure helpers (color, ANSI).
+- Use `litellm.utils.check_valid_key(model, api_key)` for credential validation — never roll a custom completion call.
+- Do not hardcode provider env-key names or model lists that already exist in the codebase. Add a `test_model` field to each provider entry to drive `check_valid_key`; set it to `None` for providers that can't be validated with a single API key (Azure, Bedrock, Ollama).
+
 ### Enterprise Features
 - Enterprise-specific code in `enterprise/` directory
 - Optional features enabled via environment variables

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

@@ -5,11 +5,76 @@ import TabItem from '@theme/TabItem';
 # Getting Started Tutorial
 
 End-to-End tutorial for LiteLLM Proxy to:
-- Add an Azure OpenAI model 
-- Make a successful /chat/completion call 
-- Generate a virtual key 
-- Set RPM limit on virtual key 
+- Add an Azure OpenAI model
+- Make a successful /chat/completion call
+- Generate a virtual key
+- Set RPM limit on virtual key
 
+## Quick Install (Recommended for local / beginners)
+
+New to LiteLLM? This is the easiest way to get started locally. One command installs LiteLLM and walks you through setup interactively — no config files to write by hand.
+
+### 1. Install
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh
+```
+
+This detects your OS, installs `litellm[proxy]`, and drops you straight into the setup wizard.
+
+### 2. Follow the wizard
+
+```
+$ litellm --setup
+
+  Welcome to LiteLLM
+
+  Choose your LLM providers
+  ○ 1. OpenAI        GPT-4o, GPT-4o-mini, o1
+  ○ 2. Anthropic     Claude Opus, Sonnet, Haiku
+  ○ 3. Azure OpenAI  GPT-4o via Azure
+  ○ 4. Google Gemini Gemini 2.0 Flash, 1.5 Pro
+  ○ 5. AWS Bedrock   Claude, Llama via AWS
+  ○ 6. Ollama        Local models
+
+  ❯ Provider(s): 1,2
+
+  ❯ OpenAI API key: sk-...
+  ❯ Anthropic API key: sk-ant-...
+
+  ❯ Port [4000]:
+  ❯ Master key [auto-generate]:
+
+  ✔ Config saved → ./litellm_config.yaml
+
+  ❯ Start the proxy now? (Y/n):
+```
+
+The wizard walks you through:
+1. Pick your LLM providers (OpenAI, Anthropic, Azure, Bedrock, Gemini, Ollama)
+2. Enter API keys for each provider
+3. Set a port and master key (or accept the defaults)
+4. Config is saved to `./litellm_config.yaml` and the proxy starts immediately
+
+### 3. Make a call
+
+Your proxy is running on `http://0.0.0.0:4000`. Test it:
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer <your-master-key>' \
+-d '{
+    "model": "gpt-4o",
+    "messages": [{"role": "user", "content": "Hello!"}]
+}'
+```
+
+:::tip Already have pip installed?
+You can skip the curl install and run `litellm --setup` directly after `pip install 'litellm[proxy]'`.
+:::
+
+---
 
 ## Pre-Requisites 
 

litellm/model_prices_and_context_window_backup.json

@@ -32354,6 +32354,53 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "xai/grok-4.20-multi-agent-beta-0309": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000,
+        "max_output_tokens": 2000000,
+        "max_tokens": 2000000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4.20-beta-0309-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000,
+        "max_output_tokens": 2000000,
+        "max_tokens": 2000000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4.20-beta-0309-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000,
+        "max_output_tokens": 2000000,
+        "max_tokens": 2000000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
     "xai/grok-beta": {
         "input_cost_per_token": 5e-06,
         "litellm_provider": "xai",

litellm/proxy/proxy_cli.py

@@ -468,6 +468,12 @@ def _maybe_setup_prometheus_multiproc_dir(
     type=str,
     help="Path to the logging configuration file",
 )
+@click.option(
+    "--setup",
+    is_flag=True,
+    default=False,
+    help="Run the interactive setup wizard to configure providers and generate a config file",
+)
 @click.option(
     "--version",
     "-v",
@@ -598,6 +604,7 @@ def run_server(  # noqa: PLR0915
     num_requests,
     use_queue,
     health,
+    setup,
     version,
     run_gunicorn,
     run_hypercorn,
@@ -611,6 +618,12 @@ def run_server(  # noqa: PLR0915
     max_requests_before_restart,
     enforce_prisma_migration_check: bool,
 ):
+    if setup:
+        from litellm.setup_wizard import run_setup_wizard
+
+        run_setup_wizard()
+        return
+
     args = locals()
     if local:
         from proxy_server import (
@@ -904,7 +917,7 @@ def run_server(  # noqa: PLR0915
         # Auto-create PROMETHEUS_MULTIPROC_DIR for multi-worker setups
         ProxyInitializationHelpers._maybe_setup_prometheus_multiproc_dir(
             num_workers=num_workers,
-            litellm_settings=litellm_settings if config else None,
+            litellm_settings=litellm_settings if config else None,  # type: ignore[possibly-unbound]
         )
 
         # --- SEPARATE HEALTH APP LOGIC ---