Break down AI inference costs by model, provider, user, and pricing tier. The Custom Reporting API gives you the data to calculate margins, track customer usage, and optimize spend across BYOK and system credentials.

Vercel is a platform for deploying modern web applications with speed and simplicity, offering developers a seamless experience for hosting and scaling their projects. With features like instant deployment, serverless functions, and global CDN, Vercel empowers developers to focus on building great user experiences without worrying about infrastructure management.

Vercel

Vercel has launched a Custom Reporting API for AI Gateway in beta for Pro and Enterprise plan users. It provides programmatic access to cost, token usage, and request volume across all AI Gateway traffic, including BYOK (Bring Your Own Key) requests. Developers can tag requests with user IDs and custom tags to break down spend by model, provider, feature, or customer. The API consolidates data from multiple providers into a single endpoint, replacing the need for manual CSV exports or third-party proxy layers. One platform reportedly saved $80K by replacing their separate proxy with this system. The reporting data enables per-customer cost tracking, usage monitoring, margin calculation, and pricing decisions based on real unit economics.

Unified reporting for all AI Gateway usage