Overview
Claude Code runs in your terminal and edits code in your project. Pointing it at Eden AI gives you:- 500+ models: switch between Claude, GPT, Gemini, and more without reinstalling
- One API key: unified billing and monitoring across providers
- Provider failover: keep working when an upstream provider has an incident
Prerequisites
- Claude Code installed (install instructions)
- Eden AI API key from app.edenai.run → API Keys
Setup
1. Export your API key
export lines to ~/.bashrc or ~/.zshrc and reload your shell.
2. Launch Claude Code
ANTHROPIC_MODEL.
Switching models
Eden AI uses theprovider/model format. Update the ANTHROPIC_MODEL environment variable (or pass --model on the command line) to switch:
GET https://api.edenai.run/v3/models.
Expert Models as Tools (MCP)
Eden AI also hosts an MCP server that exposes the expert model catalog (OCR, web search, speech, translation and more) as tools. Add it and Claude Code can read documents or search the web through the same API key:.mcp.json:
type field: without it Claude Code reads the entry as a stdio server. Run /mcp to confirm the connection. See the MCP server page for the full tool catalog and the conventions its tools share.
Troubleshooting
Authentication errors
Verify the API key is loaded in your shell and that it has LLM access:Model not found
Use the fullprovider/model string (e.g. anthropic/claude-opus-4.7, not claude-opus-4.7). Confirm the ID is in the catalog returned by GET /v3/models.
Connection issues
ConfirmANTHROPIC_BASE_URL is exactly https://api.edenai.run/v3. Check Eden AI status at app-edenai.instatus.com.
Next Steps
- Codex CLI — OpenAI’s open-source coding agent on Eden AI
- OpenCode — terminal coding agent with auto-generated config
- Chat Completions — full reference for the underlying endpoint