---
title: "What is zero data retention (ZDR) for an LLM API? | BroadRouter"
description: "Zero data retention means an AI provider does not store your prompts or outputs after a request. What ZDR covers, what is still kept, and how to check a provider."
url: https://broadrouter.com/glossary/zero-data-retention/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Zero data retention

Updated 2026-11-14

Zero data retention (ZDR) is a data-handling policy in which an AI provider processes prompts and outputs only to serve a request and does not store that content afterward, in logs, caches or training data. Content-free records such as token counts and timings are usually still kept.

Also called: ZDR, no data retention, no-log LLM API, private LLM API

Coding agents send whole repositories. Support bots send customer messages. ZDR answers the question that follows: what happens to that content after the answer comes back?

## How it works

Under ZDR, the provider holds prompt and output content only in memory while serving the request. Afterward it is not written to:

-   request or debug logs;
-   abuse-monitoring stores;
-   persistent caches or queues;
-   training or evaluation datasets.

Records that are normally still kept, without content, include request IDs, timestamps, status codes, model, [token](https://broadrouter.com/glossary/token/) counts, cost and client IP addresses.

ZDR is not a default everywhere. OpenAI’s API, for example, keeps abuse-monitoring logs for up to 30 days by default and offers ZDR to approved customers. It also says API data is not used for training unless you opt in. Read each provider’s terms rather than assuming.

## Why it matters

-   **Compliance.** Prompts often carry personal data, health details or trade secrets. Content that is never stored cannot leak from logs or backups.
-   **Fewer parties.** Every system that keeps a copy is another place to secure. A [router](https://broadrouter.com/glossary/llm-router/) or reseller adds parties to the data path.
-   **Speech and images.** Voice notes and scanned documents are among the most sensitive inputs. ZDR should cover audio and transcripts too.

ZDR protects what happens after your request arrives. You still need to protect your [API keys](https://broadrouter.com/glossary/api-key/), lock them to known IPs and redact what the model does not need.

## On BroadNet Inference

BroadNet’s docs say ZDR is “built into how we serve requests, not only stated in policy.” BroadNet Inference does not retain prompts, images, audio, answers or transcripts on any request. It keeps content-free traffic and usage records, such as timings, token counts and cost, for as long as billing, tax, security and legal obligations require. An automated retention audit runs every hour.

Per BroadNet’s privacy statement, the models it hosts run on BroadNet-owned or leased hardware in the United States, with partner capacity as backup; partner-served models run under zero-data-retention terms with US inference partners. Keys can be locked to your servers with an [IP allow list](https://broadrouter.com/glossary/ip-allow-list/).

The full list of what is and is not stored is on the [zero data retention page](https://broadrouter.com/zero-data-retention/). To compare providers, use the [10-question ZDR checklist](https://broadrouter.com/blog/zero-data-retention-llm-api-checklist/).

## Questions

### Does zero data retention mean no logs at all?

No. Providers keep operational records such as timings, token counts, cost, status codes and IP addresses for billing and security. Under ZDR those records contain no prompt or output content.

### Is ZDR the same as not training on my data?

No. Not training is a narrower promise. A provider can avoid training on your data and still keep prompts in logs for weeks. ZDR means the content is not kept at all.

### Does ZDR apply through a router?

Only if every party in the path follows it. With a hosted router, check the router's retention and that of the provider it sends your request to.

## See also

-   [API key](https://broadrouter.com/glossary/api-key/) (term)
-   [IP allow list](https://broadrouter.com/glossary/ip-allow-list/) (term)
-   [LLM router](https://broadrouter.com/glossary/llm-router/) (term)
-   [Speech-to-text](https://broadrouter.com/glossary/speech-to-text/) (term)
-   [Inference provider](https://broadrouter.com/glossary/inference-provider/) (term)
-   [Data residency](https://broadrouter.com/glossary/data-residency/) (term)
-   [Data processing agreement (DPA)](https://broadrouter.com/glossary/dpa/) (term)
-   [Subprocessor](https://broadrouter.com/glossary/subprocessor/) (term)
-   [Lock API keys to your servers with IP allow-lists](https://broadrouter.com/guides/api-keys-ip-allow-lists/) (guide)
-   [Transcribe WhatsApp voice notes to text with an API](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/) (guide)
-   [Zero data retention LLM API: a 10-question checklist](https://broadrouter.com/blog/zero-data-retention-llm-api-checklist/) (article)
-   [OpenRouter vs a flat-rate plan for AI agents: which costs less?](https://broadrouter.com/blog/openrouter-alternative-flat-rate/) (article)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-zero-data-retention&utm_content=page-cta) ·

**Sources**

-   [OpenAI, data controls in the OpenAI platform (abuse monitoring and ZDR)](https://developers.openai.com/api/docs/guides/your-data)
-   [BroadNet Inference privacy statement](https://www.broadnet.ai/inference-privacy)
-   [BroadNet Inference API reference, where your data goes](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-zero-data-retention&utm_content=sources#data)
