[BUG]: ChatGPT - gpt-5 model: 400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead. #4304
Description
How are you running AnythingLLM?
AnythingLLM desktop app
What happened?
It seems that OpenAI changed the parameter name from max_tokens to max_completion_tokens for the gpt-5 model. Because of this, gpt-5 cannot be used in AnythingLLM and returns the following error:
400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.
Are there known steps to reproduce?
Configure AnythingLLM with the gpt-5 model. Testet with desktop app v1.8.5-r2.