OpenAI

Use your favourite OpenAI in WatchThatSite.

Get your API Key

1. Go to OpenAI's API Keys page
2. Log in with your OpenAI account (create one if needed)
3. Click Create new secret key
4. Name it something descriptive (e.g., "WatchThatSite")
5. Click Create secret key
6. Copy the key immediately (it won't be shown again)

Set up billing

Ensure you have billing set up in your OpenAI account:

1. Go to Billing Settings
2. Set up a payment method or add credits
3. Set usage limits to control costs

Add to WatchThatSite

1. Go to Settings > AI Providers
2. Click Add Provider Key
3. Select OpenAI from the provider dropdown
4. Paste your API key
5. Optionally select specific models you want to allow
6. Click Save

Recommended models

Latest models with full feature support:

• GPT-4o — Latest multi-modal, vision + tool calling + streaming
• GPT-4 Turbo — Fast reasoning, 128K context, tool calling
• GPT-4 — Powerful reasoning, tool calling

Older models (gpt-3.5-turbo, etc.) are also available via your account.

All available models

Your account has access to all OpenAI models that support tool calling. See the complete list in WatchThatSite:

1. Go to Settings > AI Providers
2. Click Add Provider Key or Edit an existing one
3. Models dropdown shows all your account's available models
4. Select specific models to restrict access, or leave empty to allow all

Cost Considerations

OpenAI charges based on token usage:

• Input tokens: Price per 1K input tokens
• Output tokens: Price per 1K output tokens (typically higher)

Pricing varies by model. Check OpenAI's pricing page for current rates.

Troubleshooting

"Invalid API Key" Error

• Verify you copied the entire key without extra spaces
• Ensure the key is active (not revoked or expired)
• Check it's a secret key, not a project key

Rate Limit Errors

OpenAI enforces rate limits. If you hit limits:

• Wait before retrying
• Upgrade your account to increase limits
• Contact OpenAI support for additional quota

No Models Available

• Verify your API key has the correct permissions
• Check your account has active billing
• Ensure you have access to the specific models you're trying to use

High Costs

To reduce costs:

• Use gpt-3.5-turbo for simpler tasks
• Monitor usage in your OpenAI dashboard
• Set spending limits in your account settings