OneMux/Docs/Multimodal Input

Multimodal Input

OneMux supports image understanding, PDF document parsing, and multimodal content analysis. It works with vision models such as GPT-6.1, Claude Opus 5.5, and Gemini 4 Argon. This page explains how to upload images, parse document content, and the supported file formats and size limits.

Supported Models

Models that support multimodal input:

  • GPT-6.1 Sol, GPT-6.1 Luna
  • Claude Opus 5.5, Claude Sonnet 5.5
  • Gemini 4 Argon, Gemini 2.0 Flash

Image Understanding

Pass images using a URL or Base64:

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.onemux.net/v1"
)

response = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image.jpg"}
                }
            ]
        }
    ]
)

print(response.choices[0].message.content)

PDF Document Parsing

Some models support parsing PDF documents directly:

response = client.chat.completions.create(
    model="claude-opus-5-5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize the key information in this PDF document"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/document.pdf"}
                }
            ]
        }
    ]
)

Supported Formats and Limits

TypeSupported FormatsSize Limit
ImagePNG, JPG, JPEG, WEBP, GIFMax. 20MB
DocumentPDFMax. 20MB
Base64All image formatsMax. 20MB after encoding