On: Learning to Reason with LLMs

[natrys]

> While reasoning tokens are not visible via the API, they still occupy space in the model's context window and are billed as output tokens.

https://platform.openai.com/docs/guides/reasoning

So yeah, it is in fact very bad product design. I hope Llama catches up in a couple of months.

[AkelaWolf → natrys]

Most likely the model has similar size compared to the original gpt4, which also has similar price.