# Protecting against token theft

DevFeed: [Protecting against token theft](<https://devfeed.tech/articles/protecting-against-token-theft-771.md>)

Original publisher: [Read original article](<https://vercel.com/blog/protecting-against-token-theft>)

Author: Eric Dodds

Published: 2026-05-29T04:00:00Z

Content type: article

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>), [web applications](<https://devfeed.tech/topics/web-applications.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [apis](<https://devfeed.tech/tags/apis.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [auth](<https://devfeed.tech/tags/auth.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [vercel](<https://devfeed.tech/tags/vercel.md>), [web](<https://devfeed.tech/tags/web.md>)

## AI overview

The article explains inference theft: attackers use internet-facing AI endpoints to consume or resell someone else's paid model inference. It describes why session-based verification, rate limits, and authentication walls can fail economically, and recommends verifying every AI request, including through Vercel's BotID deep analysis.

## Source excerpt

HTTP requests are inexpensive. Vercel charges ~$2/million, a fraction of a cent per call. But a single prompt to an agent on a frontier model can cost $2, making AI a million times more expensive, and inference theft one of the highest-margin businesses an attacker can run. We have seen this type of attack on our own APIs. If you have AI endpoints exposed to the internet, the risk of abuse is high and can easily run up bills in the tens of thousands of dollars or more. Protecting those endpoints requires verification to run on every AI request, not on the session or signup. Rate limits and auth walls aren't sufficient on their own because checks that run once per session get amortized away across thousands of stolen calls. At Vercel, we gate every AI request through BotID deep analysis, and you can do the same on your own endpoints with a few lines of code. What inference theft is Inference theft is the unauthorized use of someone else's paid AI inference, either for free consumption or downstream resale. The operator pays per AI call; the attacker pays nothing for inference and then resells the tokens at a discount. This goes beyond rate-limit abuse to actual resale of a stolen resource in a market. Which AI endpoints are at risk? Any internet-facing endpoint that gives a caller meaningful control over an LLM prompt is a target. The more general the endpoint, the higher the payout per stolen call. AI playgrounds, like the AI SDK Playground, are the most dangerous shape because the caller has maximum control over the prompt, the model, and often the parameters. Stolen calls land cleanly into any standard client. Support bots and documentation assistants are less exposed when system prompts are fixed server-side, but attackers have learned how to talk the models around system prompts cheaply enough to make resale viable. Resale value tracks how easily the stolen calls can be dropped into a provider-compatible client. Why web defenses don't mitigate inference theft IP