Skip to content

fix(models): correct o4-mini pricing under chatOpenAI#6079

Merged
HenryHengZJ merged 2 commits into
FlowiseAI:mainfrom
AbdulSamad94:bugfix/fix-o4-mini-pricing
Mar 31, 2026
Merged

fix(models): correct o4-mini pricing under chatOpenAI#6079
HenryHengZJ merged 2 commits into
FlowiseAI:mainfrom
AbdulSamad94:bugfix/fix-o4-mini-pricing

Conversation

@AbdulSamad94

Copy link
Copy Markdown
Contributor

The o4-mini entry under chatOpenAI in models.json had incorrect pricing values copied from gpt-4o-mini instead of the actual o4-mini pricing.

Impact

  • Input cost was 1.5e-7 (gpt-4o-mini price), should be 1.1e-6 (~7.3× higher)
  • Output cost was 6e-7 (gpt-4o-mini price), should be 4.4e-6 (~7.3× higher)

This caused cost tracking and billing calculations to vastly underestimate the real cost by roughly 86% when users selected o4-mini.

(Note: The azureChatOpenAI section already had the correct o4-mini pricing, confirming this was an oversight in chatOpenAI.)

Changes

  • Updated packages/components/models.json: corrected input_cost and output_cost for o4-mini under chatOpenAI to match the official OpenAI pricing.

Source: Official OpenAI API Pricing, Per Collective, Price Token

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the pricing configuration for the o4-mini model in packages/components/models.json, increasing both the input and output costs. There are no review comments to address, and I have no feedback to provide.

@HenryHengZJ

Copy link
Copy Markdown
Contributor

thanks!

@HenryHengZJ HenryHengZJ merged commit 6412c20 into FlowiseAI:main Mar 31, 2026
3 checks passed
@AbdulSamad94 AbdulSamad94 deleted the bugfix/fix-o4-mini-pricing branch April 1, 2026 14:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants