Bug - gpt5 - sometime showing blank output

I found that sometime gpt5 showing blank output.

When I checked the console error came as

{“level”:30,“time”:1754842293855,“pid”:10,“hostname”:“048f18435ebc”,“msg”:“Received message”}
{“level”:30,“time”:1754842293855,“pid”:10,“hostname”:“048f18435ebc”,“msg”:“Session not found”}
{
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’
}

So seems like a bug will someone plz review as I think in GPT5 their way of accepting the parameters is bit changed so may be its creating some clashes with what we have used in past.

1 Like

Which version of OpenAI piece does flow use?

@kishanprmr I went to admin area and it says me

In my admin area it says it is
OpenAI
@activepieces/piece-openai
0.5.3

Hi @andish12
Can you try to replace the OpenAI action (or create a new one) in your flow? It should work then. Let me know if the issue persists.

I have seen this issue in newly created action too

Likewise - since the GPT5 update, our OpenAI pieces are throwing blank outputs …

we have tried re-creating the flow and disconnecting/reconnecting the api, still having the same issue … we primarily use the “Ask GPT” and “Audio Transcribe” pieces