API Reference

POST /api/analyze

Analyze an image using a vision model. Supports single or multi-model requests.

Single Model

curl -X POST https://vision.kim8.s4s.host/api/analyze \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-27b-it",
    "prompt": "Describe what you see in this image",
    "image": "https://example.com/photo.png",
    "image_type": "url",
    "temperature": 0.3,
    "max_tokens": 500
  }'

Multi-Model Comparison (up to 3 models)

curl -X POST https://vision.kim8.s4s.host/api/analyze \
  -H "Content-Type: application/json" \
  -d '{
    "models": [
      "google/gemma-3-27b-it",
      "google/gemma-3-12b-it",
      "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
    ],
    "prompt": "Analyze this screenshot for visual issues",
    "image": "https://example.com/screenshot.png",
    "temperature": 0.3,
    "max_tokens": 500
  }'

Request Parameters

model	Single model ID (required if models not set)
models	Array of model IDs for multi-model (max )
prompt	Text prompt describing what to analyze (required, max 2000 chars)
image	Image URL or base64 data URI (required)
image_type	url (default) or base64
temperature	0-2, default 0.3
max_tokens	1-4096, default 500

Single Model Response

{
  "success": true,
  "message": "Analysis complete",
  "data": {
    "content": "The image shows...",
    "model": "google/gemma-3-27b-it",
    "usage_prompt": 128,
    "usage_completion": 85,
    "time_ms": 3421.5
  }
}

Multi-Model Response

{
  "success": true,
  "message": "Multi-model analysis complete",
  "data": {
    "results": [
      {
        "model": "google/gemma-3-27b-it",
        "content": "The image shows...",
        "usage_prompt": 128,
        "usage_completion": 85,
        "time_ms": 3421.5
      },
      {
        "model": "google/gemma-3-12b-it",
        "content": "This image displays...",
        "usage_prompt": 128,
        "usage_completion": 72,
        "time_ms": 2105.3
      }
    ],
    "total_time_ms": 5532.8,
    "models_requested": 2
  }
}

GET /api/models

List all available vision models.

curl https://vision.kim8.s4s.host/api/models

Response

{
  "success": true,
  "data": {
    "models": {
      "google/gemma-3-27b-it": "Gemma 3 27B (Best quality)",
      "google/gemma-3-12b-it": "Gemma 3 12B (Balanced)",
      "google/gemma-3-4b-it": "Gemma 3 4B (Fast)",
      "mistralai/Mistral-Small-3.1-24B-Instruct-2503": "Mistral Small 3.1 24B",
      "mistralai/Mistral-Small-3.2-24B-Instruct-2506": "Mistral Small 3.2 24B (Latest)",
      "mistralai/Magistral-Small-2506": "Magistral Small 2506",
      "mistralai/Magistral-Small-2507": "Magistral Small 2507",
      "mistralai/Magistral-Small-2509": "Magistral Small 2509 (Newest)"
    }
  }
}

GET /api/health

Basic health check endpoint.

curl https://vision.kim8.s4s.host/api/health

GET /api/status

Detailed status including API connectivity, config, and uptime.

curl https://vision.kim8.s4s.host/api/status

GET /api/routes

List all available API routes.

curl https://vision.kim8.s4s.host/api/routes