[noname120]

Not true. Try to increase the context window and you will be greeted with an error when you reach the real limit enforced server-side.

[searealist]

The models themselves support up to 1M. You are just charged more for all context over 400k. The 272k limit is just a client limitation to ensure you can never go over 400k since the maximum output size of the model is 128k.

[noname120]

Not true. This is the case for the API, not for subscriptions: they are hard capped at 400k.

[quotemstr]

Perhaps not this for this parameter, but for others? Client side.

[noname120]

Apart from the local scaffolding you can configure very few parameters, and the ones you can configure are the ones that don’t matter