LLM Test Bench ("we", "our", or "the app") is a developer tool for testing and comparing large language model providers. This policy explains what data we collect, how it is used, and the choices you have.
When using Local Mode (no sign-in):
localStorage only. No data is sent to our servers.
When signed in with Google:
Your third-party LLM API keys (OpenAI, Anthropic, etc.) are sent to our backend only to proxy requests to the respective provider. They are never logged, cached beyond the request lifetime, or shared with any third party other than the target LLM provider you have chosen.
Your cloud data is retained as long as your account exists. You can delete individual history records or all history from within the app. To request full account deletion, email us at prompt2win@googlegroups.com
Data in transit is protected by TLS. Local exports are encrypted with AES-256-GCM using a password you choose (PBKDF2, 100,000 iterations). We use industry-standard practices for our Cloudflare Workers and D1 deployment.
We do not use cookies or any third-party tracking. Authentication state is stored in
localStorage (a JWT token). We do not use analytics services.
This service is not directed to children under 13. We do not knowingly collect data from children under 13.
We may update this policy from time to time. Continued use of the app after changes constitutes acceptance of the updated policy.
For privacy questions or data deletion requests, please open an issue on the project's GitHub repository or email us at prompt2win@googlegroups.com