img

Anyone knows any hacks to reduce GPT4 cost utilisation?

I have built an openAI assistant which is on GPT-4-1106-preview, as I have trained it on some books. Now the cost for that comes to $5/day at 100 threads approx. If there is anyone here who knows any hacks to reduce this cost or any workaround, then pls DM. My MVP is stuck due to this.

img

Jordon Hyrum

Stealth

10 months ago

Try quantization methods
img

Anise Olive

British petroleum

10 months ago

Cant. U get tokens which gets utilized by the size and query of data. They charge for that itself.
img

Karilyn Hyrum

Stealth

10 months ago

Buy your own compute
Sign in to a Grapevine account for the full experience.
  • Home
  • Anyone knows any hacks to reduce GPT4 cost utilisation?