Skip to main content
Back to list of integrations Use the OpenAI integration to let agents and workflows call OpenAI models for chat, assistants, vision, structured extraction, image generation, speech, and transcription.

Supported actions

Actions are OpenAI operations that an agent runs as Action Tools during a conversation. You can also run them from an Integration node in a workflow.

Prerequisites

Set up the integration

1

Create the auth profile

In Integrations, select OpenAI > Connect. On Project Auth Profiles, select New Profile > Integration Profile > OpenAI > Continue. Paste the key into API Key, keep Header Name (authorization) and Prefix (Bearer ), and select Create Profile.
2

Create the action tool

In Tools, select New Tool > Action > OpenAI > Continue. Select the Action and Auth Profile, set parameter defaults (leave a value empty for the agent to supply at runtime), and select Create Tool. Then assign the tool to an agent.

Action reference

Text and vision

Images and audio

Advanced

Troubleshoot common issues

Related articles: