ActionOpenAIUpdated May 2026

How do I use the OpenAI Responses API?

Short answer: Drop the "OpenAI → Create Response" 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	OpenAI model id
Input input	string	Required	Plain-text prompt or structured input
Instructions (system) instructions	string	Optional	Top-level instructions (replaces system role)
Max Output Tokens max_output_tokens	string	Optional	1024
Temperature temperature	string	Optional	0.7
Store Response store	options	Optional	Whether OpenAI stores the response server-side for later retrieval

Sample request

{
  "model": "{{trigger.model}}",
  "input": "e.g. Summarize the attached document",
  "instructions": "e.g. You are a helpful research assistant",
  "max_output_tokens": "1024",
  "temperature": "0.7"
}

Returns

{
  "id": "resp_abc",
  "model": "gpt-5",
  "usage": {
    "input_tokens": 10,
    "total_tokens": 60,
    "output_tokens": 50
  },
  "output": [
    {
      "role": "assistant",
      "type": "message",
      "content": [
        {
          "text": "Sample",
          "type": "output_text"
        }
      ]
    }
  ]
}

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

Triggered by

Apps that pair well as the trigger for Create Response.

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 Create Response.

What does the Create Response action do in OpenAI?

Creates a model response using OpenAI's Responses API, the unified endpoint that supersedes chat-completions for new use cases. Supports tools, vision, structured output, and file inputs in a single call.

What inputs does Create Response require?

Required: Model, Input. 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 Create Response support batch operations?

Yes. Run Create Response 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