8000 Update gptel-gemini.el models by braun-steven · Pull Request #639 · karthink/gptel · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Update gptel-gemini.el models #639

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
Merged
merged 2 commits into from
Feb 13, 2025
Merged

Update gptel-gemini.el models #639

merged 2 commits into from
Feb 13, 2025

Conversation

braun-steven
Copy link
Contributor

See #634, suggestion by @metachip.

Adds

  • gemini-2.0-flash
  • gemini-2.0-flash-exp
  • gemini-2.0-flash-lite-preview-02-05
  • gemini-2.0-flash-thinking-exp-01-21
  • gemini-2.0-pro-exp-02-05

Removes

  • gemini-2.0-flash-thinking-exp (superseded by gemini-2.0-flash-thinking-exp-01-21)

@karthink
Copy link
Owner

Thanks @braun-steven!

Instead of removing gemini-2.0-flash-thinking-exp, please "deprecate" it by changing its :description to "DEPRECATED: Please use ", and move it to the end of the model list so it shows up last. We will remove it in the release after the next.

@braun-steven
Copy link
Contributor Author

Thanks for the quick review! I've applied the changes you suggested.

@karthink karthink merged commit 86678ed into karthink:master Feb 13, 2025
@karthink karthink mentioned this pull request Feb 13, 2025
Closed
@benthamite
Copy link
Contributor
benthamite commented Feb 22, 2025 •
edited
Loading

Hi @braun-steven, I noticed you set the input and output costs of some of the new Gemini models to $0. It seems like, for Gemini, we were previously quoting the prices listed for the “paid tier” here, in which case the input and output cost should be $0.10 and $0.40, respectively. Or am I missing something? Thanks!

@metachip
Copy link

My understanding is that some models in experimental phase are not charged until the production versions are released.

@braun-steven
Copy link
Contributor Author

According to the model selection in https://aistudio.google.com/prompts/new_chat, the experimental models are all free:

SCR-20250224-hhnd-2 SCR-20250224-hhcx-2 SCR-20250224-hguu-2

@braun-steven braun-steven deleted the patch-1 branch February 24, 2025 07:13
marcbowes pushed a commit to marcbowes/gptel that referenced this pull request Mar 19, 2025
@braun-steven
gptel-gemini: Update models (karthink#639)
3f45328 
* gptel-gemini.el (gptel--gemini-models): Add new thinking models.
Deprecate `gemini-2.0-flash-thinking-exp'.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@braun-steven @karthink @benthamite @metachip
0