Vision API

Understand image and video content using multimodal models like GPT-4o and Gemini.

Usage

Pass an image URL in the content of the chat completion endpoint:

bash

curl -X POST "https://api.tk-novalink.com/v1/chat/completions" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this image?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
      ]
    }]
  }'

Supported Models

Model	Capability	Description
gpt-4o	Image understanding	OpenAI multimodal flagship
gemini-2.5-pro	Image + video understanding	Google multimodal
claude-sonnet-4	Image understanding	Anthropic vision

Audio API