AIBearisharXiv – CS AI · 14h ago7/10
🧠
Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
Researchers demonstrate that LLM providers can systematically inflate token counts billed to users, with hidden reasoning tokens inflatable by up to 1,469% without detection. The core issue stems from a fundamental audit paradox: providers control both the tokenizer and execution, making verification impossible without independent verification mechanisms like trusted execution attestation or cryptographic proofs.