Skip to main content

Image Understanding

Send images to AI models for analysis and understanding via the chat completions endpoint.

How It Works​

Vision-capable models use the same /v1/chat/completions endpoint as text models, but they accept images inside the message content. You can include an image as a data URL or a file URL, or reference a remote image by URL.

Request Format​

OneRoute supports two ways to send images:

Method 1: Data URL (Base64)​

curl https://gw.1route.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ONEROUTE_API_KEY" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA..."
            }
          }
        ]
      }
    ]
  }'

Method 2: File URL​

curl https://gw.1route.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ONEROUTE_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Describe this image in detail"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a7/Atlantic_near_Faroe_Islands.jpg/1200px-Atlantic_near_Faroe_Islands.jpg"
            }
          }
        ]
      }
    ]
  }'

Vertex AI Gemini models: when using a file URL with Vertex AI Gemini, you must specify the MIME type:

{
  "type": "image_url",
  "image_url": {
    "mime_type": "image/jpg",
    "url": "https://example.com/image.jpg"
  }
}

Response Format​

{
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The image shows a beautiful sunset over mountain ranges..."
      }
    }
  ]
}

Supported Models​

Common vision-capable models include:

  • OpenAI: GPT models, o3, o3-pro, and all o4 reasoning models
  • Anthropic: Claude 4 and 4.5 models
  • Google: Gemini 2.5 models
  • xAI: Grok 4 models

Provider Notes​

  • Most providers support both data URLs and file URLs.
  • Google AI Studio (Gemini) supports data URLs only (base64-encoded images).
  • Vertex AI Gemini requires a MIME type in the request.

Limitations​

  • Image size limits vary by provider and model.
  • File URLs must be publicly accessible.
  • Base64 data URLs increase the request payload size.
  • Image analysis responses may take longer than pure-text requests.