ActionOpenAIUpdated June 2026

How do I use OpenAI function calling?

Short answer: Drop the "OpenAIChat with Tools" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Inputs

The fields this action accepts.

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

FieldTypeRequiredDescription
Model
model
optionsRequiredModel. Options: GPT-5, GPT-4.1, GPT-4o
User Message
message
stringRequiredUser Message (required)
System Prompt
system_prompt
stringOptionalSystem Prompt
Tools
tools
arrayRequiredArray of tool definitions in OpenAI tools format. Each item: { type: 'function', function: { name, description, parameters } }
Tool Choice
tool_choice
stringOptionalauto | none | required | {"type":"function","function":{"name":"X"}}
Sample request
{
"model": "{{trigger.model}}",
"message": "{{trigger.message}}",
"system_prompt": "{{trigger.system_prompt}}",
"tools": "{{trigger.tools}}",
"tool_choice": "auto | none | required | {\"type\":\"function\",\"function\":{\"name\":\"X\"}}"
}
Returns
{
"id": "chatcmpl_abc",
"choices": [
{
"message": {
"role": "assistant",
"content": null,
"tool_calls": [
{
"id": "call_abc",
"type": "function",
"function": {
"name": "get_weather",
"arguments": "{\"city\":\"Mumbai\"}"
}
}
]
},
"finish_reason": "tool_calls"
}
]
}

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

Triggered by

Apps that pair well as the trigger for Chat with Tools.

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

FAQ

Questions about Chat with Tools.

What does the Chat with Tools action do in OpenAI?
Chat completion with tool/function calling enabled. The model may return tool_calls instead of (or in addition to) text; you execute them and feed results back as tool messages for the next turn.
What inputs does Chat with Tools require?
Required: Model, User Message, Tools. 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 with Tools support batch operations?
Yes. Run Chat with Tools 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

Other OpenAI actions.

Action
Analyze Image
Analyzes an image using GPT-4o vision, accepting a URL or base64-encoded image plus a text prompt. Use for OCR, chart extraction, alt-text generation, or visual QA.
Action
Chat Completion
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.
Action
Create Batch
Submits a batch of OpenAI requests at a 50% cost discount with a 24-hour SLA. Requires an uploaded JSONL file id with one request per line. Perfect for bulk classification or embedding jobs.
Action
Create Embedding
Generates vector embeddings for text using text-embedding-3-small or text-embedding-3-large. The de-facto embeddings default for RAG and semantic search.
Action
Create Image (DALL-E)
Generates images from a text prompt using DALL-E (or gpt-image-1). Supports size, quality, and style controls; returns a URL or base64-encoded image.
Action
Create Response
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.

Send chat with tools from your workflows.

Triggered by anything in the catalog. Free tier available. No credit card.