[FR] Add an extra parameter to in the API call to use different models #544

Closed
opened 2026-02-21 17:27:31 -05:00 by yindo · 1 comment
Owner

Originally created by @MercuryLiRC on GitHub (Sep 27, 2023).

Description of the new feature / enhancement

We have a Dify application that uses GPT4 to process tasks. There are multiple places in our own application where we call this Dify API to handle tasks for us. We want the Dify API to provide a parameter that allows us to manually specify the model we want to use in our program, so that we can reduce usage costs accordingly.

Scenario when this would be used?

On the API caller side, users can specify the desired model instead of accessing the web app and manually switching models.

Supporting information

No response

Originally created by @MercuryLiRC on GitHub (Sep 27, 2023). ### Description of the new feature / enhancement We have a Dify application that uses GPT4 to process tasks. There are multiple places in our own application where we call this Dify API to handle tasks for us. We want the Dify API to provide a parameter that allows us to manually specify the model we want to use in our program, so that we can reduce usage costs accordingly. ### Scenario when this would be used? On the API caller side, users can specify the desired model instead of accessing the web app and manually switching models. ### Supporting information _No response_
yindo added the 💪 enhancement label 2026-02-21 17:27:31 -05:00
yindo closed this issue 2026-02-21 17:27:31 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Oct 27, 2023):

Close due to it's no longer active, if you have any questions, you can reopen it.

@github-actions[bot] commented on GitHub (Oct 27, 2023): Close due to it's no longer active, if you have any questions, you can reopen it.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#544