Skip to content

Conversation

BB-BenBridges
Copy link

✨ (openAi.ts): introduce support for new GPT-5 models and adjust temperature setting based on model type to enhance AI response variability

temperature: 0,
temperature: gpt5_models.includes(this.config.model) ? 1 : 0,
top_p: 0.1,
max_tokens: this.config.maxTokensOutput
Copy link

@yasselpiloto yasselpiloto Oct 4, 2025

Choose a reason for hiding this comment

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

for the gpt-5 model family, the api expects this property to be max_completion_tokens

  error: {
    message: "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",
    type: 'invalid_request_error',
    param: 'max_tokens',
    code: 'unsupported_parameter'
  },
  code: 'unsupported_parameter',
  param: 'max_tokens',
  type: 'invalid_request_error'
}
│
└  ✖ 400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

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.

3 participants