400 error states token max is 4,096 while the openAI docs state the max is 30,000. What am I missing here? Is this related to Make being slow to adopt V2 endpoints or something else?
Welcome to the Make community!
Nope, those are (token) rate limits per minute, not model (token) limits per request.
You are confusing those two limits.
The model limits are clearly stated in the error message.
samliew – request private consultation
Join the unofficial Make Discord server to chat with us!
2 Likes