ActionOpenAIUpdated May 2026

How do I call an OpenAI chat model from a workflow?

Short answer: Drop the "OpenAI → Chat Completion" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 16 OpenAI actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Required	Which OpenAI model to use
Message message	string	Required	The user message to send
System Prompt system_prompt	string	Optional	Instructions that shape how the model responds
Temperature temperature	string	Optional	Controls randomness (0 = deterministic, 2 = very creative). Default is 1.
Max Tokens max_tokens	string	Optional	Maximum number of tokens in the response

Sample request

{
  "model": "{{trigger.model}}",
  "message": "e.g. Summarize this document...",
  "system_prompt": "e.g. You are a helpful assistant.",
  "temperature": "e.g. 0.7",
  "max_tokens": "e.g. 1024"
}

Returns

{
  "id": "chatcmpl-abc123",
  "model": "gpt-4o",
  "usage": {
    "total_tokens": 30,
    "prompt_tokens": 10,
    "completion_tokens": 20
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Chat Completion.

Any of these apps can fire this action as part of a workflow.

Google Sheets → OpenAI

2 Google Sheets triggers

HubSpot → OpenAI

18 HubSpot triggers

FAQ

Questions about Chat Completion.

What does the Chat Completion action do in OpenAI?

Sends a message and gets a response from an OpenAI chat model (gpt-4o, gpt-4o-mini, o-series, etc.). The standard chat-completion action; supports system prompts, temperature, and stop sequences.

What inputs does Chat Completion require?

Required: Model, Message. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if OpenAI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Chat Completion support batch operations?

Yes. Run Chat Completion inside a Loop node to process arrays. Tiny Command handles OpenAI's rate limits automatically so you don't have to throttle manually.

More actions