Anthropic OTPM limits estimate wiht max_tokens at the start of requests

[RyanMarten]

Still seeing rate limits on anthropic because of

OTPM rate limits are estimated based on max_tokens at the beginning of each request, and the estimate is adjusted at the end of the request to reflect the actual number of output tokens used. If you’re hitting OTPM limits earlier than expected, try reducing max_tokens to better approximate the size of your completions.

https://docs.anthropic.com/en/api/rate-limits

We need to assume max_tokens of the model when we send, but can unblock once we get a response

@adamoptimizer

Originally posted by @RyanMarten in #373 (comment)