# Paper Finds Agent Retries Inflate the True Cost of a Model Up to 4.25 Times Its Listed Price

InflationAgent measures the gap between per-token pricing and full workflow cost, and routes on a difficulty signal that predicts retries with 0.887 area under the curve.

- Published: 2026-08-18T06:24:23.025Z
- Canonical: https://polylog.news/ai/2026-08-18/paper-finds-agent-retries-inflate-the-true-cost-of-a-model-u
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CL](https://arxiv.org/abs/2608.13571)

A preprint posted to arXiv, Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems, attacks an assumption built into every model router in production. Routers pick a model by comparing advertised price per token against e…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-18/paper-finds-agent-retries-inflate-the-true-cost-of-a-model-u (subscription information: https://polylog.news/pricing).