Status | Free.ai

The status page monitors four key systems: the web server (free.ai -- Django frontend, auth, payments), the GPU server (api.free.ai -- AI model inference), the REST API for developers, and the PostgreSQL database.

The status page shows real-time system status and is checked continuously. The timestamp shows when the last check was performed.

Operational means the system is running normally with no known issues, degradation, or outages. All requests are being processed within expected response times.

If you are experiencing problems that are not reflected on the status page, please contact us through the contact form with details about what tool you were using, what you expected, and what happened. Some issues may be localized or intermittent.

No. We aim for 99.9% uptime on every plan and show live status on this page, but no plan, free or paid, currently comes with a contractual SLA or service credits.

Planned maintenance is scheduled during low-traffic hours and announced in advance. We use rolling restarts to minimize impact, and most updates are deployed with zero downtime.

If the GPU server experiences an outage, AI inference tools will be temporarily unavailable. The web server, account management, and payment systems will continue to function. We prioritize GPU server recovery and communicate updates on the status page.

Yes. Database backups run regularly and are encrypted. The web server and GPU server have redundancy built in. Enterprise customers can opt for multi-region deployments for additional redundancy.

Enterprise customers receive proactive notifications about outages and maintenance. We are working on a status notification system for all users. Currently, check this page or contact us if you experience issues.

We monitor systems 24/7. Critical incidents (full outages) are typically detected within minutes and resolved within hours. Degraded performance issues are investigated and communicated promptly.

The web server (free.ai) handles the website, user authentication, payments, and database operations. The GPU server (api.free.ai) runs all AI model inference -- every AI generation, chat completion, image, and audio generation is processed here.

The PostgreSQL database stores user accounts, token balances, chat history, API keys, payment records, and usage statistics. It does not store AI model weights or generated content long-term.