#gpt-4.1 Long Context
1 messages · Page 1 of 1 (latest)
I have not found anything there relative to how I might use the gpt-4.1 (long context) model rather than gpt-4.1
there is only one model with 1m context window. your url shows tpm meaning max tokens you are allowed to use per minute based on your tier
Yes, and I see higher tpm for gpt-4.1 (long context) in the model list, so I assumed there was a way to make use of a higher tpm someway
I'm sure a higher tier will solve my issues in the end, but that still doesn't answer what's gpt-4.1 (long context) means
Besides the organization limits fit my usage tier, so if it indicates 200k tpm at tier 1, then it must be usable in some way
hover on the info icon
Ah, so sending a 100k context request would not work as it would be above 30k tpm but below 128k, but a 150k token request would trigger the longer context and work?
yep