Skip to content

Security and governanceAnalysis

OpenRouter screens every request: what to tell your security reviewer

OpenRouter announced on 27 October 2026 that it will screen all inference requests in flight, including zero-data-retention traffic. This is a plain-language brief for security and procurement reviewers: what the published pages say, what they leave open, and how a BYOK gateway with a direct provider contract differs.

By INFRO Editorial

Published

9 min read

A grid of dark glass cards with small bar charts, a few of them lit amber, on a dark ground

In short

OpenRouter will screen every inference request in flight for CSAM, ZDR traffic included, and may retain flagged content for human review and legal preservation.1 For a reviewer, that makes ZDR a claim with a named exception, and it makes OpenRouter a content-inspecting party in the data path alongside the model provider.

Key takeaways

  • OpenRouter's own pages now describe in-flight screening of all inference requests, including ZDR traffic, with retention of flagged content as a named exception.
  • A router puts a second content-inspecting party in the data path, and its terms flow down every model provider's terms to you.
  • Retention is the sum of several layers: router metadata, opt-in logging, the provider's tier, and tools or plugins outside ZDR enforcement.
  • Ask for the terms version in force, the screening scope, and how flagged-content retention and notification work, because the pages read do not answer those.
  • A BYOK gateway is also a party in the data path; what changes is that the provider contract, account and retention settings stay yours.

What changed, in one paragraph

On 27 October 2026 OpenRouter announced that it will screen all inference requests for child sexual abuse material (CSAM) as they pass through its service. Screening happens in flight, and content flagged as potential CSAM may be retained for human review, with reporting and preservation where the law requires it.1 The announcement says this also applies to requests covered by OpenRouter's Zero Data Retention (ZDR) policy.1 Its ZDR page carries a banner calling this a planned update and says the page and the related terms are being updated.2

None of this is unusual for a service that handles user content, and the stated purpose is a legal one. For a security reviewer the question is narrower: what does it change in the data-flow diagram, in the retention answer you give your own customers, and in the evidence you can collect?

What the published pages actually say

Read together, the pages give a layered picture. Each layer is a separate answer on a questionnaire.

  • Default retention. OpenRouter says it does not store prompts or responses unless you opt in to logging or content is flagged as potential CSAM.3
  • Opt-in logging. Private input and output logging is off by default. Org admins can view all logged data for an organization; members can view their own.3
  • Opt-in use for product improvement. Off by default, offered in return for a 1% reduction in model usage cost.3
  • Sampled categorization. OpenRouter samples a small number of prompts for categorization to power reporting and model ranking. Without the product-improvement opt-in, the categorization is stored anonymously and done by a model with a zero-data-retention policy.3
  • Metadata. Token counts, latency and similar request facts are stored for every request. The page says this excludes prompt and response content.3
  • Screening. In flight, on all inference requests, with the retention exception above.1

The ZDR page adds the exception to the headline. ZDR is defined as no routine storage after processing, "apart from the CSAM exception".2 A reviewer who has a "vendor offers ZDR" line item should now read it as "ZDR with a named, legally driven exception".

What screening covers, as described

The announcement describes two mechanisms. Known-material detection compares content against hashes of previously identified CSAM. Classifiers can flag suspected material not yet in a hash database, and OpenRouter says it may retain content flagged as potential CSAM for human review, including content that does not match a known hash.1 It also states that a flag indicates suspected material and is not a determination.1

On the legal side, it cites US reporting to NCMEC's CyberTipline and a one-year preservation requirement for reported material, and says that requirement applies to reported material rather than every item flagged for review.1

Data path: two inspecting parties instead of one

With direct provider calls, your prompt reaches one party under one contract. Through a router, it reaches the router and then a model provider, and the router's terms bind you to the provider's terms as well. OpenRouter's terms say you agree to comply with each model's applicable terms, are solely responsible for reviewing them, and that continued use after a provider changes its terms counts as acceptance.4 They also say that OpenRouter may suspend access to a model if a provider requests it, and that availability is "as-available" with no guarantee.4

For a reviewer, the screening announcement adds a content-inspecting step at the router. It also states that providers may run their own screening: some may retain content for a period to run automated safety checks before anything is flagged, under their own policies.1 So a single request can be inspected at two places, by two parties, for two sets of reasons.

Retention tiers you need to map

OpenRouter describes each endpoint with three data policy tiers.2

TierWhat it meansTrained on?
ZDRNo routine storage after processing, with the CSAM exceptionNo
Safety RetentionOpenRouter or a provider may retain prompts and responses from any request, flagged or not, only to detect and prevent abuseNo
Retention and TrainingStored, and may be used for training under the provider's policyMay be
OpenRouter's endpoint data policy tiers, as published.2

Three details matter in a review.

  1. Safety Retention is not limited to flagged requests. The ZDR page says it limits why data can be kept, not whether a request has to be flagged first.2
  2. Self-serve defaults differ from enterprise defaults. If you have not chosen, self-serve accounts allow Safety Retention endpoints and enterprise accounts use ZDR only.2 Ask which one your account is on and where the setting is recorded.
  3. Unclear policy is treated conservatively. When OpenRouter cannot establish a provider's or endpoint's policy, it assumes the endpoint both retains and trains and marks it that way.2

Also note that ZDR enforcement applies to provider routing for inference. It does not cover plugins and tools you enable, such as web search, which may be run by third parties with their own retention policies.2 And OpenRouter says it has no routing rules that change on provider retention policies by themselves; you or your admin set the filters.5

Evidence: what you can and cannot hand an auditor

A security review ends in artifacts. For a router in the data path, sort them by who produces them.

QuestionEvidence sourceStatus from the pages read
Which endpoint served a request, under which data tier?Router logs and endpoint policy dataMetadata is stored per request;3 the tier is a published property of the endpoint2
Was my content retained by the router?RouterOpt-in logging is visible to admins;3 retention of flagged content is not described as visible
Did screening flag my traffic?RouterNot described
What did the provider retain?Provider policy and your agreementPublished per provider, as the provider's own terms5
Where was it processed?Regional hostnameIn-region routing for EU or US exists on Business and Enterprise plans, selected by sending requests to the regional hostname5
Evidence by source, based on the pages read on 5 November 2026.

The gaps in the third and fourth rows are the ones to write down. They do not mean the vendor will refuse; they mean the pages do not commit to an answer.

How a BYOK gateway with a direct contract differs

Be exact about the contrast, because it is easy to overstate. A BYOK gateway is still in the data path. Your requests pass through it, so it belongs on the same diagram and the same questionnaire. What differs is where the contract and the account sit.

With INFRO, you connect provider accounts you already hold, and your providers invoice you directly; INFRO takes 0% of model spend and charges a subscription for the control plane.6 Your providers process content under your own agreements and account settings, and INFRO's privacy page says it does not train on or sell your content.7 That keeps three things yours: the provider's retention and ZDR terms as you negotiated them, the provider-side logs and audit trail, and the choice of which provider accounts exist at all.

Router-side retention is also a setting you own. INFRO's content logging is off until an owner or admin turns it on; it can be limited to prompts, responses or both, and a request can set logging: false. Payload retention is the smaller of your chosen window and the plan maximum.7 The same page states that disabling INFRO logging does not disable storage or logging at your AI provider,7 which is the sentence to keep in your own diagram: two stores, two settings.

OpenRouter also supports BYOK, and a reviewer should check how it behaves. Requests on your keys still go through OpenRouter, BYOK usage carries a fee beyond a plan-dependent free allowance, and by default a failure on your key can fall back to OpenRouter's shared endpoints. Setting the fallback to "never use shared capacity" keeps requests on your account.8 If your reason for BYOK is a direct provider contract, that fallback setting decides whether the contract actually covers all traffic.

Controls that stay on your side of a gateway

These INFRO capabilities are available now and are relevant to a data-path review:

  • Provider connections. Credentials are encrypted when saved, scoped to the organization and never shown again; applications use gateway keys instead.
  • Guardrails. Pattern-based checks on prompts and responses (email addresses, card numbers, API keys, your own terms) that block, redact or flag. Detection can miss things, so it is a control, not a guarantee.
  • Model allowlists and key limits. Approve which models a project may call, and restrict a gateway key to chosen providers or IP ranges.
  • Audit log and OpenTelemetry export. Member, key and policy changes with actor and timestamp, and spans pushed to your own collector.

Some things a reviewer may ask for are not available. Regional processing, a staff access log, security event export to a SIEM, and self-hosted deployment are not shipped; treat them as roadmap or enterprise-agreement items. INFRO does not hold SOC 2 or ISO certifications. The full API contract is published in the INFRO docs (opens in a new tab) for review before any code is written, and the privacy and data page (opens in a new tab) covers logging and retention in more detail.

What to tell your security reviewer

Give the reviewer a short, dated statement rather than a link to marketing. A workable version:

Then work through this list before sign-off:

  • Redraw the data-flow diagram with the router as a content-inspecting party, plus the model provider behind it.
  • Record the terms version and date you accepted, and re-check after the announced documentation and terms update lands.
  • Confirm the account's Safety Retention setting and who can change it.
  • List every plugin and tool enabled, since ZDR enforcement does not cover them.2
  • Update customer-facing ZDR language so it names the screening exception where you repeat the vendor's claim.
  • Ask in writing how a customer is notified of retained content, and how long review retention lasts.
  • If you rely on BYOK, check the shared-capacity fallback setting on every key.
  • Decide which workloads, if any, must use a direct provider contract with no intermediary content inspection beyond your own gateway.

The last item is the real decision. Screening is a legitimate, legally anchored measure, and it does not make a router unsafe. It makes the router a party that inspects content, and that belongs in your risk record next to the provider's own retention terms.

Questions readers ask

Does OpenRouter's screening mean it stores all my prompts?
No. The announcement says flagged content may be retained for human review, reporting and legal preservation, and that the CSAM provisions do not authorize general retention of ZDR content for unrelated purposes.1 What the pages do not state is how often content is flagged or how a customer learns that something was retained; put that to the vendor.
Is in-flight screening a reason to reject a router?
Not by itself. Child-safety screening is tied to legal reporting duties, and the announcement frames it that way.1 It is a reason to update your data-flow diagram, your ZDR wording and your questionnaire, and to decide whether any workload cannot tolerate a second inspecting party.
Does using a BYOK gateway avoid third-party content inspection?
No. A gateway still receives your requests. The difference is that your provider account, contract and retention settings stay yours, and the gateway's own logging is a setting you control. INFRO's documentation says content logging is off by default and that disabling it does not change storage at your provider.7

From the team that builds it

Where this shows up in INFRO

INFRO is a control plane in front of the provider accounts you already hold. The capabilities below are the parts of it this article touches, each with the documentation that defines its behaviour.

  • Provider connections

    Available with a plan

    Connect provider accounts you already hold. Each credential is encrypted when saved, scoped to your organization and never shown again; applications use INFRO gateway keys instead.

    Read the documentation for Provider connections
  • Request traces and payload logs

    Available with a plan

    Per-request timing detail, with prompt and completion logging off by default and a retention window you choose.

    Read the documentation for Request traces and payload logs
  • Guardrails

    Available with a plan

    Pattern-based checks on chat completion prompts and responses: block, redact or flag email addresses, phone numbers, card numbers, IBANs, US Social Security numbers, IP addresses, API keys and your own terms, plus optional classifier checks on your own connection to a decision model's provider. Detection can miss things. Included on every plan.

    Read the documentation for Guardrails
  • Audit log

    Available with a plan

    Member, key, and policy changes recorded with actor and timestamp, viewable in the console.

    Read the documentation for Audit log
  • OpenTelemetry export

    Available with a plan

    Spans pushed to your own collector from the request path, with the endpoint and headers set in the console. Included on every plan.

    Read the documentation for OpenTelemetry export
  • API documentation

    Available now

    The full request and response contract for every endpoint, published in full so it can be reviewed before you write any code against it.

    Read the documentation for API documentation
  • Model allowlists

    Available with a plan

    Approve which models a project may call; anything else returns a policy error instead of a line item.

    Read the documentation for Model allowlists
  • Key limits and rotation

    Available with a plan

    Limit a gateway key to chosen providers or IP ranges, and rotate it with an overlap window so the old key keeps working while you deploy the new one.

    Read the documentation for Key limits and rotation

INFRO accounts are self-serve. Provider usage is billed to you by your providers; INFRO charges a software subscription and takes 0% of model spend. See plans.

Sources

Numbered in order of first citation. Each was opened and checked against the claim on the date shown.

  1. 1.CSAM Screening Across OpenRouter (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.
  2. 2.Zero Data Retention (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.
  3. 3.Data Collection - OpenRouter Privacy (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.
  4. 4.Terms of Service (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.
  5. 5.Provider Logging - Provider Data Retention Policies (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.
  6. 6.INFRO documentation (opens in a new tab) — INFRO. Accessed Nov 5, 2026.
  7. 7.Privacy & data (opens in a new tab) — INFRO. Accessed Nov 5, 2026.
  8. 8.BYOK - Bring Your Own Keys to OpenRouter (opens in a new tab) — OpenRouter. Accessed Nov 5, 2026.

About this article

Read on 5 November 2026: OpenRouter's data collection, provider logging, ZDR, BYOK and terms pages, its 27 October 2026 CSAM screening announcement, and INFRO's docs overview and privacy page. The terms page was returned truncated, so nothing beyond the sections read is claimed; screening effective dates, notification practice and OpenRouter's attestations were left out as unconfirmed.

Last checked against its sources on . The next review is due by . No separate named reviewer is recorded for this article.

How articles are written, sourced and corrected is set out in the editorial standards.