FAQ

Does the gateway store my prompts?

Yes, in the requests browser, for the team that owns the API key. Prompts are stored for the configured retention window (default 30 days). You can disable prompt persistence per team in /teams/<id>/settings.

Which models are supported?

OpenAI's GPT-4o family, the o-series reasoning models, the Anthropic Claude family (Opus, Sonnet, Haiku), and Google's Gemini Pro and Flash. New providers land as the gateway adds support.

Can I bring my own provider keys?

Yes, and you should. Per-org provider credentials live in /providers, encrypted at rest. The gateway uses your keys for upstream calls and bills you against the provider's actual usage, so the gateway stays revenue-neutral on the upstream side.

Is there a free tier?

The gateway is open source and self-hostable for free. The hosted plan is free for self-serve teams on BYOK, with a $70/mo Team plan adding alerting and org-scoped access controls, and Enterprise for on-prem and SOC2. See /pricing.

How do I correlate a gateway error with a request?

Every response includes an X-Request-Id header. Search /requests?request_id=<id> to see the full pipeline trace.