Choosing the right ChatGPT (OpenAI) action to send messages
- Tables
-
Product updates
Product updates: January 2023 Product updates: March 2023 Product updates: February 2023 Product updates: April 2023 Product updates: May 2023 Product updates: June 2023 Product updates: July 2023 Product updates: August 2023 Product updates: September 2023 Product updates: October 2023 Product updates: November 2023 Product updates: December 2023 Product updates: January 2024 Product updates: February 2024 Product updates: March 2024 Product updates: April 2024 Product updates: May 2024 Product updates: June 2024 Product updates: July 2024 Product updates: August 2024 Product updates: September 2024 Product updates: October 2024 Product updates: November 2024 Product updates: December 2024 Product updates: January 2025 Product updates: February 2025 Product updates: March 2025 Product updates: April 2025 Product updates: May 2025 Product updates: June 2025 Product updates: July 2025 Product updates: August 2025
- Zaps
- Your Zapier account
- Interfaces
- Canvas
- Chatbots
- Getting started
- Agents
- MCP
- Built-in tools
- Lead Router
- Apps
Table of Contents
This article will guide you through the differences between available ChatGPT (OpenAI) actions you can use in your Zap to send and receive messages. It will help you decide which action is best for your needs when sending messages. There are three actions available:
- Conversation (Responses API).
- Conversation with Assistant.
- Send Prompt
ChatGPT (OpenAI) action comparison table
Feature | Conversation (Responses API) | Conversation with Assistant | Send Prompt |
Best for | Conversations that require back-and-forth interactions. Includes memory and optional image support. | Conversations with structured assistants that can store files, use tools, and maintain long context. | Simple, one-off prompts that do not need memory or media. |
Context retention | Supports memory via the Memory Key field. | Supports memory via the Conversation ID field and assistant-specific instructions. | No support for context retention. Each request is independent. |
API used | Responses API | Assistant API | Completion API |
Supported models |
|
||
Media support | Images supported (if model allows, e.g. GPT-4o). | Supports file uploads (code interpreter and file search). | No media support. |
Tool support | N/A |