OpenAI File Upload

Upload files to OpenAI for use with assistants, fine-tuning, and batch.

Overview

OpenAI File Upload uses the OpenAI Files API (POST /files) to upload files for various purposes including assistants, fine-tuning, batch processing, and vision. Accepts binary file input and uploads it as multipart/form-data with a specified purpose. Returns the file object with id, filename, bytes, purpose, and status metadata. The file ID can be used in subsequent OpenAI API calls.

Category: AI
Tool Name: openai_file_upload
Version: 1

Appearance: Icon: openai | Color: #10a37f

Node Type

Action (Binary) — handles file/binary data operations

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

This tool requires OpenAI credentials. See the Credentials Guide for setup instructions.

Parameters

Parameter	Type	Required	Default	Description
Binary Property Name	string	No	data	The name of the binary property containing the file to upload. Names are case-sensitive — see the upstream node’s Binary Data panel for the exact names to use.
Purpose	options	No	assistants	The intended purpose of the uploaded file. This determines how OpenAI processes and validates the file.
				Options: assistants (use with OpenAI Assistants), fine-tune (training file for fine-tuning a model), batch (input file for batch processing), vision (image file for vision analysis)
Options	collection	No	{}	Optional output settings — add only the fields you need.
— Response Field Name	string	No	file	The output field name where the file upload response will be stored.
Include Input	boolean	No	false	Whether to include the original input item fields in the output alongside the upload response.
Max Concurrency	number	No	5	Maximum number of items to process concurrently.

Output Data

One output item per input item. The full file object lands on the field named by Response Field Name (file by default), and the two fields you almost always need — fileId and fileName — are lifted to the top level. The rest of the input item JSON is dropped unless Include Input is on; the input binary is forwarded unchanged.

{
  "file": {
    "id": "file-abc123",
    "object": "file",
    "bytes": 120432,
    "filename": "training.jsonl",
    "purpose": "fine-tune",
    "status": "processed"
  },
  "fileId": "file-abc123",
  "fileName": "training.jsonl"
}

• fileId is the value other OpenAI nodes expect. Wire it into OpenAI Chat, OpenAI Reasoning, OpenAI Structured Output, OpenAI Vision or OpenAI Code Interpreter as {{ $json.fileId }}.
• Uploading the same file twice creates two distinct file IDs — OpenAI does not deduplicate. Upload once and reuse the ID across runs where you can.

Usage Examples

• Upload a JSONL file for fine-tuning an OpenAI model
• Upload a document for use with an OpenAI assistant
• Upload a batch processing input file to OpenAI
• Upload an image file for OpenAI vision analysis
• Upload training data and get the file ID for a fine-tuning job

Example Configuration

Upload a file arriving on the default binary property:

{
  "type": "openai_file_upload",
  "parameters": {
    "binaryPropertyName": "data",
    "purpose": "assistants"
  }
}

Upload fine-tuning data and keep the original item fields:

{
  "type": "openai_file_upload",
  "parameters": {
    "binaryPropertyName": "trainingFile",
    "purpose": "fine-tune",
    "includeInput": true,
    "options": {
      "responseFieldName": "uploadedFile"
    }
  }
}

Upload an image for a later vision step:

{
  "type": "openai_file_upload",
  "parameters": {
    "binaryPropertyName": "photo",
    "purpose": "vision",
    "maxConcurrency": 10
  }
}

Error Handling

Mode	Behavior
stop	Halts workflow on first error
continue	Skips failed items, passes successful ones through
errorPort	Routes failed items to Error output port

Tips

OpenAI File Upload sends binary files to the OpenAI Files API as multipart/form-data with a specified purpose such as assistants, fine-tuning, batch processing, or vision. Use this tool when a downstream OpenAI operation requires a pre-uploaded file reference, such as attaching documents to an assistant or supplying training data for a fine-tune job. It returns a file object with the id, filename, byte size, purpose, and status fields, where the file id is passed directly into subsequent OpenAI API calls.