Frequently Asked Questions

VisionAI is an enterprise-grade computer vision API platform that enables developers to detect objects, recognize faces, extract text (OCR), and analyze images using state-of-the-art AI models. We offer REST APIs and SDKs in Python, Node.js, Go, and Java.

We support JPEG, PNG, WebP, BMP, TIFF, and GIF formats. Images can be up to 20MB in size and 10,000 x 10,000 pixels. We also support base64-encoded images via the API.

Our P50 latency is 32ms and P99 latency is under 50ms for standard image classification. Object detection typically takes 50-80ms depending on the number of objects. We serve from edge locations in North America, Europe, and Asia-Pacific.

Yes! The Starter plan includes 1,000 free API calls per month. No credit card required. It includes object detection and image classification features.

On the Starter plan, additional calls are blocked until the next billing cycle. On Pro and Enterprise plans, overage is billed at a per-call rate. We send alerts at 80% and 95% usage.

Yes, you can change plans at any time. Upgrades are effective immediately with prorated billing. Downgrades take effect at the start of the next billing cycle.

We offer official SDKs for Python, Node.js, Go, Java, and Ruby. Community-maintained SDKs are available for C#, PHP, and Swift. All SDKs are open-source and available on GitHub.

Starter: 10 requests/second, Pro: 100 requests/second, Enterprise: custom rate limits up to 10,000 requests/second. Rate limit headers are included in every API response.

By default, images are processed in memory and not stored. Enterprise customers can opt into temporary storage for batch processing. We are SOC 2 Type II certified and GDPR compliant. See our Privacy Policy for details.