Thanks a lot! this helps understand it (although I don’t understand why this information is not disclosed anywhere…) Seems the 85 token per low image is really misleading on their docs.
A simple section like below
For a single image
detail:lowrequest,
You get billed = 85 tokens
You get counted for rate limit (TPM) = 764 tokens (meaning for Tier 1, you can only do 30,000/764 = ~38 max images per minute) - which explains my observation hitting the limit with 39 images here Tried everything with RateLimitError: Error code: 429 with gpt4-o - #2 by ruki
would be more than enough of a clarification. This really should be in the docs I think.
On that note, for my use-case where i need to send around 30k frames, well I can’t… Even with the highest tier because of how the tokens are calculated for rate limit. I have to think of an alternative way.
The maximum
detail:lowimages that could be sent (with the 10M TPM) (with even Tier 5) is,10,000,000/764 = ~13k images
Am I right about the above?