aiqbench analysis
Zero Data Retention (ZDR) establishes a critical boundary for AI developers by guaranteeing that inference providers do not persist prompts or responses, though it does not prevent data transmission or ensure third-party tool compliance. Understanding the distinction between provider-side retention guarantees and local logging controls is essential for building privacy-preserving applications in an era where data handling policies vary by endpoint.
Zero Data Retention (ZDR): What It Means for AI APIs

ZDR means an AI provider processes your prompt, returns a response, and doesn't store either one afterward. It's a retention guarantee, not a universal privacy policy. This page explains the boundary, compares ZDR with related controls, and shows how to enforce it at the account, guardrail, or request level.
Zero Data Retention (ZDR) means an AI provider processes your prompt, returns a response, and doesn’t store it afterward. It’s a retention guarantee. It doesn’t keep data inside your network, control what your application logs, or automatically cover third-party tools connected to the request. This page explains what ZDR covers, what it doesn’t, and how to enforce it on your API calls. ZDR prevents an eligible inference provider from retaining your prompts and responses. Your data still reaches the provider and is processed by the model. On OpenRouter, you can enforce ZDR through account settings, guardrails, or the provider.zdr request field. ZDR applies to provider inference. Your logs, enabled tools, plugins, and other storage features require separate controls. What is zero data retention (ZDR)? Zero Data Retention is a data-handling policy under which an AI provider processes your request without persisting the prompt or response. ZDR governs provider-side retention. It doesn’t mean your…
Excerpt shown under the publisher's RSS terms · 153 words · full text and figures are on the publisher's site
Related coverage

[AINews] Opus 5.5 is good at explainer videos
Latent Space · Sep 29, 2026

[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026

Why “zero data retention” may not protect your business data
Proton Blog · Oct 8, 2026

What Is an LLM Gateway? The Missing Layer Between Your App and AI Models
OpenRouter · Jun 11, 2026