OpenAI

The OpenAI preset sends chat-completions requests directly from Sythoria's Rust backend to OpenAI. OpenAI receives the prompt, included conversation context, attachments, credential, and ordinary request metadata under your account and OpenAI's current terms.

Configure Sythoria#

1. Create a project-scoped key from the OpenAI API key page.
2. Set an account budget and review data controls before using private content.
3. In Sythoria, open Settings, add a model, and select OpenAI.
4. Confirm the preset, paste the key, save, and run the connection check.

The default is an application preset, not a statement about OpenAI's newest model. Model IDs, account eligibility, input types, context limits, prices, and deprecation dates change independently. Select an exact ID shown in the official OpenAI model documentation or your account.

Key handling#

Sythoria encrypts the key in secrets.enc; the root encryption key is kept in the operating system credential vault. Use a separate provider key for Sythoria where possible, restrict its project and budget, and revoke it if it appears in a prompt, log, screenshot, shell history, or repository.

Troubleshooting#

Do not solve an authentication error by sending the key to a support issue.