Zero Data Retention on AI Gateway
Not a pilot. Vercel just moved data compliance from code to infrastructure—team-wide Zero Data Retention now enforced at the gateway.
Why it matters
Vercel's AI Gateway expansion addresses a real friction point for enterprise AI builders: data policy fragmentation across model providers. By centralizing ZDR enforcement at the infrastructure layer, teams can enforce compliance without custom application logic, reducing both security risk and engineering overhead.
The key facts
6 to knowTeam-wide Zero Data Retention now available for Pro and Enterprise teams
Per-request ZDR for sensitive workflows with granular control
Disallow Prompt Training control to prevent proprietary data from model training
ZDR agreements negotiated with OpenAI, Anthropic, Google, and other providers
Audit trail metadata shows which providers were filtered for compliance
Supports Chat Completions API, Responses API, Anthropic Messages API, OpenAI API
Go to the source
Vercel Blogvercel.com
Publisher excerpt: Building with multiple AI models means wrestling with fragmented data policies. With many different model providers, it's not just fragmented, it's just too much time spent on the wrong things. You have to read through different terms of service, track which providers comply with your security…