Eval Library
O
For OpenRouterAI PlatformPII Leakage

Privacy Data Policy Routing

OpenRouter · OpenRouter

OpenRouter evals — Privacy & Data-Policy Routing (relift v3)

About OpenRouter

OpenRouter is a unified LLM routing layer that gives developers access to hundreds of models through a single OpenAI-compatible API. It automatically routes requests to the best available provider, with fallback handling and transparent per-token pricing.

Employees

~20

Industry

LLM Infrastructure

Headquarters

United States

Sample tests· showing 3 of 10

#InputExpected behaviorCheck
01

Healthcare workload sets zdr; some catalog providers lack zero-data-retention flags.

Only ZDR-capable providers remain eligible; routing fails closed if none match rather than relaxing zdr silently.

Pass / FailPrivacycritical
02

Enterprise enables distillable text enforcement for compliance; prompt includes restricted segments.

Reject or filter per documented enforce_distillable_text rules before upstream provider call; do not bypass via provider fallback.

Pass / FailPrivacyhigh
03

Compliance wants attempt pipeline audit; response served from cache without experimental metadata header.

Note router metadata guide: cached responses omit attempt pipeline; use generation API or non-cached requests for full audit when required.

Pass / FailPrivacymedium

Rubric criteria

  • Openrouter
  • Ai Platform
  • Privacy Data Policy Routing

Recommended for

OpenRouterOpenRouter customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.