The great game of chicken is afoot. Fable 5 trial period is extended, yet again, to July 19th. Albeit anecdotal, there are numerous developers sharing similar stories about the cost performance of the new ChatGPT model, GPT-5.6 Sol. The community consensus agrees Fable 5 and Sol are both frontier models delivering similar results. What’s staggering in these accounts of ChatGPT comparison is not its mere performance. The current consensus seems to be running around a third or a quarter of the cost of running Fable 5.

The landscape of the frontier models does paint more favorable pictures for the end users. If you don’t mind switching from one model to another, there are open-source context compression tool-kit projects with one of the main features being switching between models made easier. Some of them even offer agent compatibility, where different agents share config or memory. If Anthropic keeps extending the trial, you may jump between Fable 5 and Sol with the added benefit of subsidy from subscription tiers from both companies.

For Anthropic, however, I must say, I don’t see what their plea to the market is with Fable. It’s no longer the most capable — certainly Sol has divided the room. It’s not the cheapest — ChatGPT pricing takes that throne easily. Fable 5 is being positioned as a flagship premium model that is inaccessible with subscription (again, different from Sol), and the only thing keeping up the premise of ‘consider Fable as well’ is its current trial period. Because most vibe coders would swap as soon as Fable leaves subscription again. Same capability, quarter the cost.