OpenAI

Generate text, create embeddings, and moderate content with the OpenAI API.

Detail	Value
Category	AI
Base URL	https://api.openai.com/v1
Authentication	Bearer Token
Endpoints	6
Connector key	openai

Using OpenAI in a workflow

1. Go to Connections and click New Connection.
2. Pick OpenAI from the marketplace.
3. Enter your credentials (see Authentication above for what's expected).
4. In a workflow, drop an API Call node and select this connection.
5. Pick the operation you need from the Operation dropdown. The full list is below.

Available endpoints

Endpoint	Summary
POST /chat/completions	Create a chat completion
POST /embeddings	Create an embedding vector
POST /images/generations	Generate an image
POST /moderations	Classify text for moderation
GET /models	List available models
POST /audio/transcriptions	Transcribe audio to text

Each endpoint is documented in full below. Use the outline on the right to jump to one.

POST /chat/completions

Create a chat completion

Detail	Value
Operation ID	ai.createChatCompletion
Method	POST
Path	/chat/completions

Parameters

No parameters.

Request Body

Field	Type
model	string
messages	array
temperature	number

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.createChatCompletion.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked: fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.

POST /embeddings

Create an embedding vector

Detail	Value
Operation ID	ai.createEmbedding
Method	POST
Path	/embeddings

Parameters

No parameters.

Request Body

Field	Type
model	string
input	string

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.createEmbedding.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked: fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.

POST /images/generations

Generate an image

Detail	Value
Operation ID	ai.generateImage
Method	POST
Path	/images/generations

Parameters

No parameters.

Request Body

Field	Type
model	string
prompt	string
n	integer
size	string

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.generateImage.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked: fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.

POST /moderations

Classify text for moderation

Detail	Value
Operation ID	ai.createModeration
Method	POST
Path	/moderations

Parameters

No parameters.

Request Body

Field	Type
input	string
model	string

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.createModeration.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked: fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.

GET /models

List available models

Detail	Value
Operation ID	ai.listModels
Method	GET
Path	/models

Parameters

No parameters.

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.listModels.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.

POST /audio/transcriptions

Transcribe audio to text

Detail	Value
Operation ID	ai.transcribeAudio
Method	POST
Path	/audio/transcriptions

Parameters

No parameters.

Request Body

Field	Type
file	string
model	string

Using this endpoint in a workflow

1. Add an API Call node to your workflow.
2. Pick your OpenAI connection from the Connection dropdown.
3. In the Operation dropdown, select ai.transcribeAudio.
4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked: fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream OpenAI API reference.