Use supported cloud-based model providers

This page outlines the steps for using the integration with supported cloud-based AI model providers.

To use the APIs of supported cloud-based model providers, you must have an active account with sufficient credits or a subscription for API usage with the chosen provider. Note that account creation and credit management are handled externally and are outside the scope of this guide.

Using this feature involves transmitting selected HTTP traffic, prompts, and chat messages to the selected provider’s servers. Review each provider’s privacy policy to understand its data handling and retention practices. If you handle sensitive information or require local processing, consider using a local model option instead.

To configure and use a cloud-hosted model provider, follow these steps:

1. Go to the Provider settings tab.

2. Select a cloud-hosted model provider from the Model provider dropdown.

3. Enter the API key for the selected provider in the API key field. Refer to the selected provider’s documentation for instructions on obtaining and managing your API key.

4. Keep the default Base URL, or override it if your provider account requires a custom endpoint.

5. In the Model field, type or select the exact model identifier supported by the chosen provider.

6. Use Read timeout to control how long the extension waits for a provider response. Set it to 0 for no timeout.

7. The Request parameters field accepts a JSON object with valid model parameters such as temperature, top_p, stop, and max_tokens. For details, see the selected provider’s documentation.

8. Click Test request before using the provider for scanning or AI Chat.

The AI scanner tab controls the scan prompt and message role used for scan requests. Provider settings are shared by active scanning, manual scanning, provider tests, and AI Chat.