alt Hacker NewsI'm not sure the tokens can be compared like that between OpenAI/Anthropic.
When i swapped between a 200k Fable context into an Astra model (i was out of fable) the token usage in that context dropped to 150k or something.
Either there was a bug somewhere, or the same text got cut up very differently between providers.
That 50k was almost certainly accumulated encrypted reasoning tokens that would have been unreadable by astra.