Files

The files endpoint stores a file once so you can reference it by id in any number of chat requests instead of re-encoding the bytes into every message. It follows the OpenAI files schema, so the openai SDK's files methods work without modification — all uploads and storage are free.

Upload a file#

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/api/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

uploaded = client.files.create(
    file=open("report.pdf", "rb"),
    purpose="user_data",
)
print(uploaded.id)  # reference this id in chat requests

Reference it in a chat request#

Send a file content part carrying the file_id — the server inlines the bytes for you:

completion = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize this document."},
                {"type": "file", "file": {"file_id": uploaded.id}},
            ],
        }
    ],
)

Notes#

• Max 32 MB per file, 256 MB storage per account; files expire after 30 days.
• Supported types: images (png, jpeg, webp, gif), audio (mp3, wav, flac, m4a, ogg, aac), PDF, and plain text.
• The model must support the file's modality — vision for images, audio input for audio, file/PDF input for documents.
• client.files.list(), client.files.retrieve(id), and client.files.delete(id) manage stored files — see the Files guide for the full surface.

Also see#

• Files guide — endpoints, limits, and reference semantics
• Files reference