This directory contains sample Claude Code settings configurations for different setups.
All configurations include:
- Custom base URLs or API endpoints for different providers
- Authentication token placeholders
- Model specifications for each provider
- Disabled telemetry and non-essential traffic for development
Configuration for using Claude Code with GitHub Copilot proxy setup. Points to localhost:4141 for the Anthropic API base URL.
Configuration for using Claude Code with LiteLLM gateway setup. Points to localhost:4000 for the Anthropic API base URL.
Configuration for using Claude Code with Qwen models via Alibaba's DashScope API. Uses the Qwen3-Coder-Plus model through a claude-code-proxy.
Configuration for using Claude Code with SiliconFlow API. Uses the Moonshot AI Kimi-K2-Instruct model.
Configuration for using Claude Code with Google Cloud Vertex AI. Uses Claude Opus 4 model with Google Cloud project settings.
Configuration for using Claude Code with DeepSeek v3.1 (via DeepSeek's official Anthropic-compatible API).
Configuration for using Claude Code with Azure AI (Anthropic-compatible endpoint). Points to Azure AI services endpoint.
Configuration for using Claude Code with Azure AI Foundry native mode. Uses CLAUDE_CODE_USE_FOUNDRY flag with Claude Opus 4.1 + Sonnet 4.5 model.
Configuration for using Claude Code with MiniMax API. Uses the MiniMax-M2 model.
Configuration for using Claude Code with OpenRouter API. OpenRouter provides access to many models through a unified API. Note: ANTHROPIC_API_KEY must be explicitly blank while ANTHROPIC_AUTH_TOKEN contains your OpenRouter API key. By default, Claude Code uses Anthropic model aliases (Sonnet, Opus, Haiku), which OpenRouter automatically maps. You can override with custom models using ANTHROPIC_DEFAULT_SONNET_MODEL, ANTHROPIC_DEFAULT_OPUS_MODEL, and ANTHROPIC_DEFAULT_HAIKU_MODEL.