OOmnistu

Blog / AI Development

AI Development

Runaway AI usage: unbounded consumption, denial of wallet and how to cap them

Plan usage limits, spending controls and monitoring for AI features that can consume costly resources through abuse or mistakes.

OOmnistu
Reviewed 2026-11-16 · 2 min read
Uncontrolled inference is the risk
OWASP lists the consequences as denial of service, economic loss, model theft and service degradation - high LLM compute costs invite resource abuse.
Denial of wallet
High-volume use exploits pay-per-use cloud AI pricing, creating unsustainable costs for the provider.
Cap spend, not just rate
An alert is not a hard spending cap; enforceable usage and spend limits must exist alongside provider-level alerts.

All wording checked against the OWASP LLM Top 10 entry (LLM10) linked in Sources; no statistics, prices or vendor claims.

Uncontrolled requests to an AI feature can drive high cost and load, up to the limits of the application, infrastructure and provider account. OWASP lists this as LLM10, Unbounded Consumption, in its Top 10 for LLM Applications (2025). We read the project's page in full on 15 November 2026, and not its references. This article summarises that page.

What it is

OWASP describes it as an LLM application allowing excessive, uncontrolled inference, with consequences it lists as denial of service, economic loss, model theft and service degradation. It says the high compute demands of LLMs, especially in the cloud, make them open to resource abuse.

Examples listed on the page

  1. Variable-length input flood: many inputs of varying length overload the system.
  2. Denial of wallet: high-volume use exploits pay-per-use cloud AI pricing, creating unsustainable costs for the provider.
  3. Continuous input overflow: inputs beyond the context window waste compute.
  4. Resource-intensive queries: demanding inputs drag out processing.
  5. Model extraction via API: crafted queries collect enough output to copy part of a model.
  6. Functional model replication: using the model to generate training data for another model.
  7. Side-channel attacks that use input filtering behaviour to learn about the model.

Variable-length input flood

Many inputs of varying length overload the system.

Denial of wallet

High-volume use exploits pay-per-use pricing, creating unsustainable costs.

Continuous input overflow

Inputs beyond the context window waste compute.

Resource-intensive queries

Demanding inputs drag out processing.

Model extraction via API

Crafted queries collect enough output to copy part of a model.

Functional replication

Using the model to generate training data for a copy.

Mitigations listed

The page does not rank these or say how much each helps. We do not either.

Practical questions for a product team

Related: API rate limiting and resource limits, cloud cost control for startups, prompt injection explained.

Limits

One OWASP page. References unread. No statistics, prices or vendor claims. Several items (watermarking, glitch tokens, adversarial training) are named by the page without detail and we add none.

By Omnistu.

Sources

Previous
Can an AI feature leak private data? Sensitive information disclosure explained