Chat Completion

Send a conversation to a model on Gemini Enterprise Agent Platform and get the next reply

Use it in a workflow

Add a step and choose the Gemini Enterprise Agent Platform connector.
Pick the Chat Completion action (under ai).
Fill in the fields below, then reference the result from later steps as {{chatCompletion.response.data}}.

modelstringrequired

A model id, e.g. gemini-2.5-flash, or a Claude model such as claude-sonnet-4-5. It must be enabled in your project, in the connection's location.

temperaturenumber

0 is focused and repeatable, higher is more varied. Leave empty for the model's default.

maxTokensnumber

Longest reply, in tokens.

Default 1024

messagesstringrequired

JSON list of messages, e.g. [{"role": "system", "content": "Be brief."}, {"role": "user", "content": "Hello"}].

Need more? See the Gemini Enterprise Agent Platform guide for connection setup and behaviour shared by every action.

Was this page helpful?