Analyze and extract information from various file types including documents, spreadsheets, and PDFs
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | ✅ Yes | gpt-4.1 | The model to use for the request. Must support file analysis capabilities. |
input | array | ✅ Yes | - | Array of message objects with role and content. Each message contains: - role: “user” or “assistant” - content: Array of content objects supporting the following types: - input_text: Text prompt with text field - input_file: File input with file_url field, supports: - Direct URL to publicly accessible files: https://oss.heyoos.com/ai-draw/material/Essential-English.pdf - Base64 encoded files: data:{mime-type};base64,{base64_string} - Supported formats: PDF, DOCX, XLSX, TXT, CSV, JSON, XML, HTML - Maximum file size: 20MB Example with direct file URL: json [ { "role": "user", "content": [ { "type": "input_text", "text": "Please analyze this file and extract the key information" }, { "type": "input_file", "file_url": "https://oss.heyoos.com/ai-draw/material/Essential-English.pdf" } ] } ] |
stream | boolean | ❌ No | false | Whether to stream the response |