AIToday
Large Language ModelsAI Safety & AlignmentITmedia AI+Published: Nov 19, 2026, 13:01 JST

Shadow APIs: 11 of 24 endpoints ran wrong models, CISPA finds

Send on LINE
Shadow APIs: 11 of 24 endpoints ran wrong models, CISPA finds

3 Key Points

  1. What happened

    Researchers from CISPA and the University of Waterloo identified 17 shadow APIs used in 187 academic papers; fingerprinting found 11 of 24 endpoints (45.83%) were not the model advertised, including 'GPT-5' endpoints matching GLM-4-9B or Qwen2.5-7B.

  2. Why it matters

    For researchers who rely on these cut-price intermediaries because official APIs are costly or region-blocked, results may reflect a model other than the one they believe they are testing, undermining reproducibility.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The study, titled "Real Money, Fake Models: Deceptive Model Claims in Shadow APIs," arrives as researchers increasingly turn to unofficial channels to access models like GPT-5 and Gemini-2.5 that are costly or restricted in certain regions. The team found that 15 of the 17 shadow APIs were run by individuals with opaque identities, and 4 had already ceased operations, highlighting the instability of these services as a research foundation.

The fingerprinting results are particularly striking: endpoints sold as GPT-5 or GPT-4o-mini matched the fingerprints of cheaper open-source models such as GLM-4-9B and Qwen2.5-7B, and requests to DeepSeek-Reasoner behaved like DeepSeek-Chat without a thinking mode. Separately, even when fingerprints matched the advertised model, accuracy on medical and legal benchmarks fell sharply in some cases, suggesting that substitution is not the only risk.

With about 62% of the 187 papers using these APIs accepted at peer-reviewed venues like ACL, CVPR, and ICLR, the findings raise questions about the reliability of results that depend on shadow APIs. The concentration of users at Chinese institutions points to access restrictions as a key driver, and the unpredictable safety-test deviations add another layer of concern for researchers assessing model behavior.

FAQ
What are shadow APIs?
They are unofficial intermediary services that offer cheap access to official LLM APIs without regional restrictions, according to the paper.
How did researchers detect model substitution?
They used fingerprinting of AI response patterns and statistical tests on outputs to identify the model actually running behind each endpoint.
Were all shadow APIs unreliable?
Some services matched official scores on non-reasoning tasks, but reasoning performance dropped sharply for one service, and 4 of the 17 services had already shut down.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMeta's Muse agent sends users other people's data, staff posts show