Last Update: 2025/3/26

Gizmo OpenAI Uploaded API

The Gizmo OpenAI Uploaded API allows you to upload a file to a specific conversation.

Endpoint

POST https://platform.llmprovider.ai/v1/uploaded

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body

The request body should be a FormData object with the following parameters:

Parameter	Type	Description
conversation_id	string	The ID of the conversation.
upload_type	string	The type of the upload. my_files or multimodal
files	multipart.FileHeader	The file to be uploaded(file maxsize <= 20M). multimodal: "image/webp", "image/jpeg", "image/gif", "image/png" my_files: "application/vnd.openxmlformats-officedocument.presentationml.presentation", "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "application/json", "text/x-tex", "application/x-latext", "text/plain", "application/pdf", "text/x-java", "text/markdown", "text/x-script.python", "text/x-ruby", "application/msword", "text/javascript", "text/x-php", "text/x-typescript", "text/x-sh", "text/x-c++", "text/x-csharp", "text/x-c", "text/html"
model	string	The model to be used.(gizmo-gpt-4o)

Request Example

POST /api/gizmo/upload HTTP/1.1
Content-Type: multipart/form-data; boundary=----WebKitFormBoundary7MA4YWxkTrZu0gW

------WebKitFormBoundary7MA4YWxkTrZu0gW
Content-Disposition: form-data; name="conversation_id"

12345
------WebKitFormBoundary7MA4YWxkTrZu0gW
Content-Disposition: form-data; name="upload_type"

image
------WebKitFormBoundary7MA4YWxkTrZu0gW
Content-Disposition: form-data; name="files"; filename="example.png"
Content-Type: image/png

<file content>
------WebKitFormBoundary7MA4YWxkTrZu0gW
Content-Disposition: form-data; name="model"

gizmo-gpt-4o
------WebKitFormBoundary7MA4YWxkTrZu0gW--

Response Body

The response body will be a JSON object containing the generated completions and other metadata.

Field	Type	Description
id	string	Unique identifier for the uploaded file.
name	string	Name of the uploaded file.
size	int64	Size of the uploaded file in bytes.
download_url	string	URL to download the file (optional).
image_width	int	Width of the image (optional).
image_height	int	Height of the image (optional).
use_case	string	Use case of the file (optional).
fileTokenSize	int	Token size of the file (optional).
mimeType	string	MIME type of the file.
conversation_id	string	ID of the conversation (optional).

Response Example

{
  "id": "12345",
  "name": "example.png",
  "size": 12345,
  "download_url": "https://platform.llmprovider.ai/v1/download/12345",
  "image_width": 800,
  "image_height": 600,
  "use_case": "my_files",
  "fileTokenSize": 100,
  "mimeType": "image/png",
  "conversation_id": "12345"
}

Example Request

Shell

curl -X POST https://platform.llmprovider.ai/v1/uploaded \
-H "Authorization: Bearer $YOUR_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F "upload_type=my_files" \
-F "files=@/root/ceshi.txt" \
-F "model=gizmo-gpt-4o"

nodejs

const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/uploaded';

const formData = new FormData();
formData.append('upload_type', 'my_files');
formData.append('files', fs.createReadStream('/root/ceshi.txt'));
formData.append('model', 'gizmo-gpt-4o');

const headers = {
    'Authorization': `Bearer ${apiKey}`,
     ...formData.getHeaders(),
};

axios.post(url, formData, { headers })
.then(response => {
    console.log('Response:', response.data);
})
.catch(error => {
    console.error('Error:', error);
});

python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/uploaded'

headers = {
    'Authorization': f'Bearer {api_key}'
}

files = {
    "files": open("/root/ceshi.txt", "rb")
}

data = {
    "upload_type": "my_files",
    "model": "gizmo-gpt-4o"
}

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    print('Response:', response.json())
else:
    print('Error:', response.status_code, response.text)

For any questions or further assistance, please contact us at [email protected].