diff --git a/docs/my-website/docs/tutorials/claude_responses_api.md b/docs/my-website/docs/tutorials/claude_responses_api.md index 668398537ba..171e86fff51 100644 --- a/docs/my-website/docs/tutorials/claude_responses_api.md +++ b/docs/my-website/docs/tutorials/claude_responses_api.md @@ -1,25 +1,58 @@ import Image from '@theme/IdealImage'; +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; -# Call Responses API models on Claude Code +# Claude Code This tutorial shows how to call the Responses API models like `codex-mini` and `o3-pro` from the Claude Code endpoint on LiteLLM. +:::info -Pre-requisites: +This tutorial is based on [Anthropic's official LiteLLM configuration documentation](https://docs.anthropic.com/en/docs/claude-code/llm-gateway#litellm-configuration). This integration allows you to use any LiteLLM supported model through Claude Code. + +::: + +## Prerequisites - [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview) installed -- LiteLLM v1.72.6-stable or higher +- API keys for your chosen providers +## Installation + +First, install LiteLLM with proxy support: + +```bash +pip install 'litellm[proxy]' +``` ### 1. Setup config.yaml +Create a secure configuration using environment variables: + ```yaml model_list: - - model_name: codex-mini - litellm_params: - model: openai/codex-mini - api_key: sk-proj-1234567890 - api_base: https://api.openai.com/v1 + # Responses API models + - model_name: codex-mini + litellm_params: + model: openai/codex-mini + api_key: os.environ/OPENAI_API_KEY + api_base: https://api.openai.com/v1 + + - model_name: o3-pro + litellm_params: + model: openai/o3-pro + api_key: os.environ/OPENAI_API_KEY + api_base: https://api.openai.com/v1 + +litellm_settings: + master_key: os.environ/LITELLM_MASTER_KEY +``` + +Set your environment variables: + +```bash +export OPENAI_API_KEY="your-openai-api-key" +export LITELLM_MASTER_KEY="sk-1234567890" # Generate a secure key ``` ### 2. Start proxy @@ -30,11 +63,13 @@ litellm --config /path/to/config.yaml # RUNNING on http://0.0.0.0:4000 ``` -### 3. Test it! (Curl) +### 3. Verify Setup + +Test that your proxy is working correctly: ```bash curl -X POST http://0.0.0.0:4000/v1/messages \ --H "Authorization: Bearer sk-proj-1234567890" \ +-H "Authorization: Bearer $LITELLM_MASTER_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "codex-mini", @@ -42,21 +77,97 @@ curl -X POST http://0.0.0.0:4000/v1/messages \ }' ``` -### 4. Test it! (Claude Code) +### 4. Configure Claude Code -- Setup environment variables +Setup Claude Code to use your LiteLLM proxy: ```bash export ANTHROPIC_BASE_URL="http://0.0.0.0:4000" -export ANTHROPIC_API_KEY="sk-1234" # replace with your LiteLLM key +export ANTHROPIC_API_KEY="$LITELLM_MASTER_KEY" ``` -- Start a Claude Code session +### 5. Use Claude Code + +Start Claude Code with any configured model: ```bash +# Use Responses API models +claude --model codex-mini +claude --model o3-pro + +# Or use the latest model alias claude --model codex-mini-latest ``` -- Send a message +Example conversation: + +## Troubleshooting + +Common issues and solutions: + +**Claude Code not connecting:** +- Verify your proxy is running: `curl http://0.0.0.0:4000/health` +- Check that `ANTHROPIC_BASE_URL` is set correctly +- Ensure your `ANTHROPIC_API_KEY` matches your LiteLLM master key + +**Authentication errors:** +- Verify your environment variables are set: `echo $LITELLM_MASTER_KEY` +- Check that your OpenAI API key is valid and has sufficient credits + +**Model not found:** +- Ensure the model name in Claude Code matches exactly with your `config.yaml` +- Check LiteLLM logs for detailed error messages + +## Using Multiple Models + +Expand your configuration to support multiple providers and models: + + + + +```yaml +model_list: + # Responses API models + - model_name: codex-mini + litellm_params: + model: openai/codex-mini + api_key: os.environ/OPENAI_API_KEY + api_base: https://api.openai.com/v1 + + - model_name: o3-pro + litellm_params: + model: openai/o3-pro + api_key: os.environ/OPENAI_API_KEY + api_base: https://api.openai.com/v1 + + # Standard models + - model_name: gpt-4o + litellm_params: + model: openai/gpt-4o + api_key: os.environ/OPENAI_API_KEY + + - model_name: claude-3-5-sonnet + litellm_params: + model: anthropic/claude-3-5-sonnet-20241022 + api_key: os.environ/ANTHROPIC_API_KEY + +litellm_settings: + master_key: os.environ/LITELLM_MASTER_KEY +``` + +Switch between models seamlessly: + +```bash +# Use Responses API models for advanced reasoning +claude --model o3-pro +claude --model codex-mini + +# Use standard models for general tasks +claude --model gpt-4o +claude --model claude-3-5-sonnet +``` + + + \ No newline at end of file diff --git a/docs/my-website/docs/tutorials/github_copilot_integration.md b/docs/my-website/docs/tutorials/github_copilot_integration.md index 97c01e5ccf6..fc2682df6f9 100644 --- a/docs/my-website/docs/tutorials/github_copilot_integration.md +++ b/docs/my-website/docs/tutorials/github_copilot_integration.md @@ -1,11 +1,11 @@ --- -sidebar_label: "Use LiteLLM with GitHub Copilot" +sidebar_label: "GitHub Copilot" --- import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; -# Use LiteLLM with GitHub Copilot +# GitHub Copilot This tutorial shows you how to integrate GitHub Copilot with LiteLLM Proxy, allowing you to route requests through LiteLLM's unified interface. diff --git a/docs/my-website/docs/tutorials/litellm_gemini_cli.md b/docs/my-website/docs/tutorials/litellm_gemini_cli.md index bf8e2cb44cb..a36d898d7da 100644 --- a/docs/my-website/docs/tutorials/litellm_gemini_cli.md +++ b/docs/my-website/docs/tutorials/litellm_gemini_cli.md @@ -1,4 +1,4 @@ -# Use LiteLLM with Gemini CLI +# Gemini CLI This tutorial shows you how to integrate the Gemini CLI with LiteLLM Proxy, allowing you to route requests through LiteLLM's unified interface. diff --git a/docs/my-website/docs/tutorials/openai_codex.md b/docs/my-website/docs/tutorials/openai_codex.md index bb5af956b0c..41416f85159 100644 --- a/docs/my-website/docs/tutorials/openai_codex.md +++ b/docs/my-website/docs/tutorials/openai_codex.md @@ -2,7 +2,7 @@ import Image from '@theme/IdealImage'; import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; -# Using LiteLLM with OpenAI Codex +# OpenAI Codex This guide walks you through connecting OpenAI Codex to LiteLLM. Using LiteLLM with Codex allows teams to: - Access 100+ LLMs through the Codex interface diff --git a/docs/my-website/docs/tutorials/openweb_ui.md b/docs/my-website/docs/tutorials/openweb_ui.md index a55a913bbe1..fa8e3cdad29 100644 --- a/docs/my-website/docs/tutorials/openweb_ui.md +++ b/docs/my-website/docs/tutorials/openweb_ui.md @@ -2,7 +2,7 @@ import Image from '@theme/IdealImage'; import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; -# Open WebUI with LiteLLM +# Open WebUI This guide walks you through connecting Open WebUI to LiteLLM. Using LiteLLM with Open WebUI allows teams to - Access 100+ LLMs on Open WebUI diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js index 7b7e712d910..85a000f760f 100644 --- a/docs/my-website/sidebars.js +++ b/docs/my-website/sidebars.js @@ -213,7 +213,7 @@ const sidebars = { type: "category", label: "Secret Managers", items: [ - "set_keys", + "secret", "oidc" ] },