BroadRouter
Get started

Zero data retention LLM API: a 10-question checklist

By the BroadNet Inference team · 5 min read · Published · Updated

A zero-data-retention LLM API processes your prompts and outputs for the request and does not store them afterwards, in logs, caches or training sets. Ask what is kept (usually content-free usage records), for how long, who runs the GPUs and how retention is checked. BroadNet Inference keeps no prompts, images, audio or answers and checks hourly that its gateway is configured to keep no content.

A glass enclosure with an input entering and a response leaving, labelled "Private inference".

Coding agents send whole repositories. Support bots send customer messages. Transcription pipelines send phone calls. Before any of that goes to an LLM API, someone will ask: what happens to it after the answer comes back? “Zero data retention” (ZDR) is the answer people want to hear, but the phrase covers very different practices.

What should zero data retention cover?

Content that should not outlive the request:

  • Prompts, system prompts and tool results
  • Images and audio
  • Model outputs and transcripts
  • Full request and response bodies, including in debug logs
  • Raw URLs, query strings and authentication values

Records that are normally kept, and should be content-free:

  • Request IDs, timings, HTTP status, byte counts
  • Account and key IDs, model, token counts, cost
  • Client IP addresses, for security

If a provider can’t tell you which list each item is on, treat that as a “no”.

Are training, retention and ZDR the same promise?

Promise What it means What it doesn’t mean
“Not used for training” Your data won’t train future models It may still be stored for a while
“Retained for N days” Content is kept, then deleted Staff or systems may access it meanwhile
“Zero data retention” Content isn’t stored after the request Metadata is still kept

The large providers show why the difference matters. For a side-by-side of official wording from several providers, see LLM API data retention compared. OpenAI’s data controls page says that since March 1, 2023, API data is not used to train its models by default. The same page says abuse monitoring logs “are retained for up to 30 days”, that ZDR controls “are subject to prior approval by OpenAI”, and that endpoints which store state, such as files, assistants and batches, are not eligible. A provider can be honest on all three points and still keep your content for a month by default.

Where do ZDR promises usually have gaps?

  • Eligibility. ZDR may need approval, a specific plan or a contract, and is off until it’s switched on.
  • Endpoint scope. Chat may qualify while file storage, batches or fine-tuning don’t.
  • Safety carve-outs. OpenRouter’s FAQ, for example, defines ZDR as “no routine storage of prompts or responses after processing, apart from a CSAM exception”.
  • Layers above the model. A gateway, router or observability tool in between may log prompts even if the model provider doesn’t. Ask every layer.
  • Your own systems. Your app logs, error trackers and analytics often keep more content than the provider does.

What 10 questions should you ask a provider?

  1. Are prompts and outputs stored after the request? Anywhere? Include logs, caches, queues and backups.
  2. Is any content used for training or evaluation? By you or by a model vendor?
  3. What do you keep, field by field? Ask for the list.
  4. How long are usage records kept, and why?
  5. Who runs the GPUs? Your provider, a cloud, or a reseller’s reseller?
  6. Which subprocessors can see request content?
  7. How is retention verified? A policy, or an automated check?
  8. Can keys be locked to my IP addresses? A leaked key is a data path too.
  9. Where is the hardware, and is regional placement available?
  10. What happens on a support ticket? Can staff see content when you report a bug?

Ask for the answers in writing, and note which document makes them binding: the terms, a privacy statement or a signed agreement.

How does BroadNet Inference answer them?

Question BroadNet Inference
Prompts, images, audio, answers stored No; processed for the request and not retained
Training on your data No; the privacy statement rules out training, fine-tuning and evaluation on inference data
What’s kept Content-free traffic, usage and account records (full list)
How long records are kept As long as billing, tax, security and legal obligations require
Verification Gateway configuration checked hourly for content-free operation
Hardware The privacy statement says hosted models run on “BroadNet-owned or leased hardware in the United States, with partner capacity as backup”; partner-served models run under ZDR terms with US inference partners
Data residency Agree processing locations with BroadNet before sending data with residency requirements (GDPR checklist)
Key protection IP allow-lists, up to 32 entries; changes and revocations apply to new requests within five seconds
Stored keys SHA-256 hashes only; the raw key is shown once

BroadNet’s docs describe zero data retention as “built into how we serve requests, not only stated in policy”. It applies to every request, with no setting to switch on. The details are in the privacy statement.

Does ZDR cover speech and Arabic audio?

Voice is the most sensitive input most products handle: a voice note can contain a name, a phone number and a health detail in ten seconds. If you transcribe calls or WhatsApp voice notes, ask the same ten questions about audio and transcripts. See the Arabic speech-to-text buyer’s guide.

How do you check a provider’s answers?

  1. Read the privacy statement and the API reference, not only the marketing page. Look for a field-by-field list.
  2. Check the scope. Which models, endpoints and plans does the promise cover?
  3. Look at what the API returns. If a dashboard shows your past prompts, they are stored somewhere.
  4. Ask about the support process. Who can see what when you open a ticket?
  5. Write the answers into your vendor record, with links and the date you checked.

What does ZDR not fix?

Zero data retention protects what happens after your request reaches the provider. You still need to:

  • Keep API keys on servers, never in browsers or mobile apps
  • Lock keys to your egress IPs with an IP allow-list
  • Redact what the model doesn’t need, such as card numbers (how to redact before sending)
  • Log request IDs on your side, so you can debug without the provider storing content; the errors guide shows what to send support

When you move an app from one provider to another, add these checks to the migration checklist. If you route through a gateway, ask it the same questions; the OpenRouter comparison shows how one router handles ZDR.

Where BroadNet Inference fits

BroadNet Inference suits teams that want ZDR on every request without applying for it, including on partner-hosted models, which its privacy statement says run under zero-data-retention terms with US inference partners. It keeps content-free records for billing and security, as every provider does. If you need your data processed in a specific region, agree processing locations with BroadNet before you send data; the default for its own and hosted models is the US.

Questions

What does zero data retention mean for an LLM API?

The provider processes your prompts, files and outputs to answer the request and does not store that content afterwards, including in logs, caches, backups or training sets. Content-free records such as timings and token counts are usually still kept.

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. Zero data retention means those records contain no prompt or output content.

Is "we don't train on your data" the same as zero data retention?

No. A provider can promise not to train on API data and still keep it for a period, for example for abuse monitoring. OpenAI's docs say API data is not used for training by default, and that abuse monitoring logs are retained for up to 30 days.

Are my prompts used to train models on BroadNet Inference?

No. BroadNet's privacy statement says it does not use inference data "to train, fine-tune or evaluate models", and prompts, images, audio, answers and transcripts are not retained after the request.

Is zero data retention enough for GDPR?

It helps but does not settle it by itself. You still need a lawful basis, a record of processing and an agreement with each processor. Ask your data protection lead; ZDR reduces what a provider holds, not your own obligations.

Where does BroadNet run its models?

BroadNet's privacy statement says its own and hosted open-weight models 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. Contact BroadNet to agree processing locations before sending data with residency requirements.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity