This Step uses the ChatGPT API with its latest and most advanced gpt-3.5-turbo and gpt-4 models. It processes spreadsheets.
Inputs
Das sind die Optionen, mit denen man den Step konfigurieren kann.
Name
Datentyp
Beschreibung
Pflichtfeld
Werte
account
ACCOUNT
Your OpenAI Account
Nein
input
SPREADSHEET
Limits the spreadsheet rows to be processed.
Ja
mappingdefinition
STRING
The mapping definition JSON String
Ja
Folgende Felder sind zu konfigurieren:
Feld
Datentyp
Beschreibung
Pflichtfeld
Standardwert
id
SINGLE
An identifier (e.g. ProductID, SKU) to identify the record after the OpenAI result was returned.
Nein
message
SINGLE
The message is basically the text you are sending to the ChatGPT chat API.
Ja
model
STRING
The model which will generate the completion. Only the chat models can be used.
Nein
gpt-5.2
gpt-5.1
gpt-5
gpt-5-nano
gpt-5-mini
gpt-4.1
gpt-4.1-nano
gpt-4.1-mini
gpt-4
gpt-4-turbo-preview
gpt-4o
gpt-4o-mini
gpt-4o-search-preview
gpt-4o-mini-search-preview
gpt-3.5-turbo
o1
o3-mini
reasoning_effort
STRING
Reasoning Effort is a new API parameter in GPT-5 that allows developers to directly control how much invisible internal thinking work (reasoning tokens) the model performs before giving its final answer – the higher the value, the more thorough and accurate, but also slower and more expensive the answer. Default: none
Nein
none
minimal
low
medium
high
limit
STRING
limits the spreadsheet rows to be processed
Nein
max_tokens
STRING
Max. number of tokens to return per row.
Nein
variance
STRING
The variance determines the randomness of the generated output. None outputs a pure deterministic result. Which means the same command or question always arises the same result. Low results in a more deterministic ouput with little variance. High increases the result variance.
Ja
none
low
medium
high
very high
maximum
Outputs
Das sind die Ergebnisse des Steps, die von nachfolgenden Steps, nach der Ausführung verwendet werden können.
