Connect OpenClaw to Eden AI and route your agent through 500+ models with smart routing, automatic fallbacks, and a single API key.Documentation Index
Fetch the complete documentation index at: https://www.edenai.co/docs/llms.txt
Use this file to discover all available pages before exploring further.
Overview
OpenClaw is a terminal-based AI coding agent. By pointing it at Eden AI, you get:- 500+ models: Access OpenAI, Anthropic, Google, and more through a single API key
- Smart routing: Use the
@edenaimodel to automatically pick the best provider per request based on quality, latency, cost and live provider health - Automatic fallbacks: Requests reroute to healthy providers if one goes down
Prerequisites
- OpenClaw already installed. If not, see the OpenClaw install guide
- Eden AI API key from app.edenai.run → API Keys
Setup
1. Add Eden AI as a custom provider
OpenClaw stores its config at~/.openclaw/openclaw.json (on Windows: %USERPROFILE%\.openclaw\openclaw.json). Open it in your editor of choice and add the Eden AI provider with the @edenai smart-router model:
@edenai is Eden AI’s smart router. For every request it picks the best-performing model based on quality, latency, cost and live provider health. How smart routing works →
A few notes on the config above:
nameis just the display label shown in OpenClaw’s model picker. If you later switchidto a specific model (e.g.anthropic/claude-sonnet-4-5), rename this field too so the picker doesn’t show a stale label.costvalues are placeholders. Billing is handled on the Eden AI side through your API key, so OpenClaw’s local cost tracking isn’t used here. Check per-request cost in the Eden AI dashboard.supportsTools: trueenables tool/function calling through Eden AI. Set it tofalseonly if you want to restrict this provider to plain chat completions.
2. Configure OpenClaw interactively
Run the built-in wizard:@edenai (Custom Provider) — the provider you defined in Step 1. Accept the defaults for the remaining steps (Workspace, Gateway, Channels, etc.) unless you have specific local-networking or channel needs.
The wizard’s Gateway step configures OpenClaw’s local server (port, bind address, auth mode, tailscale exposure) — it does not ask for the Eden AI API URL. That’s already set as
provider.edenai.baseURL in Step 1.3. Start OpenClaw
Using specific models
@edenai handles routing automatically, but you can target a specific model by replacing the id with a provider/model string:
| Model | Best for |
|---|---|
@edenai | Default — smart routing across all providers |
anthropic/claude-sonnet-4-5 | Balanced reasoning |
anthropic/claude-opus-4-7 | Maximum capability |
anthropic/claude-haiku-4-5 | Fast and cheap |
openai/gpt-5 | OpenAI’s frontier model |
google/gemini-2.5-pro | Long context, multimodal |
Troubleshooting
401 Unauthorized
Verify your Eden AI key — grab a fresh one at app.edenai.run → API Keys. Check for leading/trailing spaces.
model not found
Ensure the id uses the provider/model format (or @edenai for the smart router). No bare model names.
Connection issues
Confirm the base URL is exactlyhttps://api.edenai.run/v3/llm and check Eden AI status at app-edenai.instatus.com.
Next Steps
- Claude Code - Official Claude CLI
- OpenCode - Terminal-based AI coding assistant
- Cline - Autonomous AI coding agent for VS Code