investigation
On easy tasks solved at every effort level, costs can be up to 42x higher in API costs because the model treats effort as a fixed token multiplier.
A investigation by החוקרים. Statements are as reported by the cited publishers — not verified by DecisionGateway.
שם תחטפו קנס של עד פי 42 בעלויות ה-API
Discussion
Related claims
Between 58% and 98% of the true cost of running an agent at high effort is not the AI bill but the opportunity cost of developers' time waiting for the model.החוקרים · investigationRaising reasoning effort improves average benchmark scores but produces painful performance drops at the individual task level; tasks solved easily and cheaply at Low fail at High or xHigh.החוקרים · investigationTurning off thinking entirely (None level) is sometimes more expensive than Low, because the agent compensates with a four-times-longer action chain that inflates the context window and input token bill.החוקרים · investigationThis is a direct price/performance escalation in frontier AI, and if the real-world gains hold, advanced-model economics improve for coding, research and agent workflows while competitors face pressure to answer on both capability and cost.post author · predictionIn coding with high Effort, Fable 5.2 reaches the same level as today's flagship models at half the cost.انتروپیک · statementGemini 4 Carbon costs more than 2 times less than the next-best external model.post author · statement