Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[2][Medium][Server+App] When user runs out of funds, they should be switched to a cheaper model #4

Open
nang-dev opened this issue Sep 2, 2024 · 2 comments
Open

[2][Medium][Server+App] When user runs out of funds, they should be switched to a cheaper model #4

nang-dev opened this issue Sep 2, 2024 · 2 comments

Comments

@nang-dev
Copy link

nang-dev commented Sep 2, 2024 •
edited by Fryingpannn
Loading

  • Implement GPT3.5 turbo in our server as a model choice (best cheapest model)
  • If user run out of funds, indicate in popup that user is automatically switched to GPT3.5 Turbo since they ran out of funds, and they can top up on the landing page to continue using premium models.
  • Automatically switch the user to GPT3.5 turbo which we'll allow unlimited requests of.
@Fryingpannn Fryingpannn changed the title When user runs out of funds, they should be switched to the cheap model [2][Medium][Server+App]When user runs out of funds, they should be switched to the cheap model Sep 13, 2024
@Fryingpannn Fryingpannn changed the title [2][Medium][Server+App]When user runs out of funds, they should be switched to the cheap model [2][Medium][Server+App] When user runs out of funds, they should be switched to a cheaper model Sep 13, 2024
@Fryingpannn Fryingpannn transferred this issue from another repository Sep 13, 2024
@andrewjhopkins
Copy link

andrewjhopkins commented Sep 19, 2024 •
edited
Loading

I can grab this

Never mind I see a PR was opened https://github.com/trypear/pearai-server/pull/210

@Ellahinator
Copy link

We should use gpt-4o-mini as it's much cheaper and better performance than gpt-3.5-turbo.

https://context.ai/compare/gpt-4o-mini/gpt-3-5-turbo

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
San Francisco V2 Release Quest (please comment on issue you'd like to start. First number on tasks indicates priority (highest is 0))
Status: Todo
Milestone
No milestone
Development

No branches or pull requests
3 participants
@nang-dev @andrewjhopkins @Ellahinator