Status & Uptime
Status · Uptime · Live Health

Status & uptime.
Real-time API health.

Live /health check against our production Modal API, refreshed every 60 seconds. Transparent component status, an honest incident-response policy, and a real human on call. No fake green lights. If /health stops responding, the badge below turns red within a minute.

Last reviewed: 2026-05-07 On-call: modelbrewai@gmail.com

Production API health.

The badge below is fetched directly from the Modal-hosted FastAPI /health endpoint by your browser. There is no caching layer between you and the live response. If the request fails, the badge says so.

Checking… Endpoint: fourwheels2512--crma-finetune-fastapi-app.modal.run/health
Contacting the API…
Your browser is calling the production Modal endpoint directly. This page does not proxy or cache the result.
Last checked: HTTP: Latency:

What we monitor.

Five components carry traffic for ModelBrew. The dates below are the most recent date a human or smoke test verified the component end-to-end — not a claim of zero downtime in between.

API fourwheels2512--crma-finetune-fastapi-app.modal.run
What we check: GET /health returns 200 with {"status":"healthy"}. Live-fetched on this page every 60 s.
Verified 2026-05-07
App app.modelbrew.ai
What we check: Cloudflare Pages serves the Next.js static export; signup, login, dashboard, and run-launch flows render without console errors.
Verified 2026-05-07
Marketing site modelbrew.ai
What we check: this page, /security, /claims, /finetuning, and /continual all return 200 from Cloudflare Pages with their canonical content.
Verified 2026-05-07
LLM Judge Gemini 2.5 Flash
What we check: the cleaner's judge / rewriter / polarity-pair calls succeed end-to-end against Google's Gemini 2.5 Flash API on a smoke fixture.
Verified 2026-05-07
Payments Stripe webhook
What we check: POST /stripe/webhook verifies signatures, the credit-grant path is idempotent, and a synthetic checkout-session event credits the test account.
Verified 2026-05-07

What happens when something breaks.

Incident response policy

Detection — The live badge on this page is the first public signal. Internal smoke checks and Modal's own platform alerts are the second. The founder is paged via email on the on-call address.

Notification — For incidents that impact billing or a user's ability to launch a paid run, we email each affected user from modelbrewai@gmail.com within 1 business day of detection — whether or not the incident is fully resolved by that point.

Auto-refund — If a fine-tuning or continual-learning run gets stuck (no heartbeat past the active-job window), the backend auto-refunds the held credits within ~90 minutes. The refund path is in backend/server.py (_auto_refund) and is logged with a correlation ID so the operator can reconcile against Stripe.

Postmortem — For incidents lasting more than 1 hour or involving data exposure, we publish a short postmortem (cause, blast radius, fix, prevention) on the blog within 7 days.

Subscribe to incident notifications.