Short answer: Drop the "Anthropic → Upload File" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
File URL file_url | string | Required | Public HTTPS URL the executor will fetch and upload as the file body. Anthropic's Files API requires a real binary upload — pass a URL that returns the raw file bytes (PDF, image, text, etc.). Signed S3 / CDN URLs work; one redirect is followed. |
Filename (optional) filename | string | Optional | Override the filename Anthropic stores. If empty, the executor derives it from the URL's path. |
{"file_url": "e.g. https://example.com/files/report.pdf","filename": "e.g. report.pdf"}
{"id": "file_abc","filename": "report.pdf","mime_type": "application/pdf","created_at": "2026-05-10T10:00:00Z","size_bytes": 12345}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.