Preview docs. Hallucination Guard is the only live endpoint today.
The rest of the API surface ships through the rest of 2026. Join the waitlist to be first in line and shape what we build first.
Resources
Support
How to reach a human, what to expect on response times by tier, and the status page for ongoing incidents.
For pre-launch waitlist questions: hello@useprism.com. Once the API tier ships, paid-tier customers get a private support email per environment. Include the request ID from any failed call (returned in the error body). That's the fastest path to a real diagnosis.
Response times
- Hobbyist: community support via GitHub Discussions (link goes here at launch).
- Startup: email support, 1 business day median.
- Scale: priority email, 4 business hours median.
- Enterprise: dedicated Slack channel + 1-hour incident response per contract.
Status page
status.prism.dev goes live alongside the API tier and tracks per-endpoint uptime + active incidents. Subscribe by email or RSS.
Reporting a bug
The most useful bug report has: the endpoint, the input that triggered the issue, the response (including the request_id), and what you expected. We diagnose request IDs across our log infrastructure in seconds. They short-circuit hours of back-and-forth.
Feature requests
Currently directed at the developer waitlist . The "What are you building?" field is read by a human and informs the roadmap. Once the API tier launches, feature requests move to GitHub Discussions.