How to Use DevToks with OpenClaw

Connect OpenClaw to a single API boundary so agent workflows and application traffic share the same operational surface.

Step 1: Get Your API Key

Go to the dashboard
Sign up or log in to your account
Navigate to API Keys -> Create New Key
Copy the key

Step 2: Install OpenClaw

macOS / Linux / WSL2

curl -fsSL https://openclaw.ai/install.sh | bash

Windows (PowerShell)

iwr -useb https://openclaw.ai/install.ps1 | iex

Verify the installation:

openclaw --version

Step 3: Configure OpenClaw with DevToks

Option A: Non-interactive (recommended)

openclaw onboard \
  --auth-choice custom-api-key \
  --custom-base-url https://api.devtoks.com/v1 \
  --custom-api-key sk-your-key \
  --custom-compatibility openai \
  --install-daemon

Option B: Interactive wizard

Run the configuration wizard and select a custom provider when prompted:

openclaw config

Step 4: Verify the Gateway

Check that the OpenClaw Gateway is running and connected. Then open the dashboard.

openclaw gateway status
openclaw dashboard

Step 5: Start Coding

Run OpenClaw in any project directory:

# Explain the codebase
openclaw message "Explain what this project does"

# Generate new functionality
openclaw message "Add rate limiting to the API endpoints"

# Debug issues
openclaw message "Find the source of this memory leak"

Advanced: Switch Models

List available models from DevToks, set a default model, or call GET /v1/models directly for the full list.

openclaw models list --provider custom
openclaw models set gpt-4.1

Or call GET /v1/models directly for the full list:

curl https://api.devtoks.com/v1/models \
  -H "Authorization: Bearer sk-your-key"

Troubleshooting

Gateway not starting - Verify --custom-base-url has no trailing slash and run openclaw gateway status for details.
Invalid API key - Use your DevToks key, not a direct provider key. Re-run openclaw config to update the stored credential.
Outage - Check status.