Observed arrival · 2026-11-16
RelayLens puts LLM relays under test
A black-box testing tool for checking what third-party Claude and OpenAI API relays actually serve.
- For
- Developers using third-party LLM API relays
- Worth noticing
- The page recommends a temporary, limited-quota API key and says keys are used for one request, never stored or logged.
Field notes
The page describes a black-box check: enter a relay’s base URL and API key, choose Claude or OpenAI, and start detection; it says the key is used for that request only and recommends a temporary, limited-quota key. Checks named in the page and metadata include model identity, possible downgrades, tokenizer fingerprints, usage or billing, and long-context needle tests. RelayLens explicitly frames results as heuristic judgments tied to the test moment, not a definitive provider verdict.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue