Visionati API
One integration, multiple AI models. Describe, tag, and moderate images in your app without building ML infrastructure.
Multiple AI Models
Access Claude, Gemini, OpenAI, Grok, Google Vision, Amazon Rekognition, Clarifai, and more through one API. Enable multiple models per request and compare outputs to find what works best.
Sync or Async
Single images return immediately. Batch requests and videos process asynchronously. Poll for results when ready.
Roles & Custom Prompts
Use built-in roles like Ecommerce, Realtor, or Caption. Or send your own custom prompt for complete control over the output.
160+ Languages
Get descriptions in any language. Specify the output language in your request and AI models respond accordingly.
Simple Integration
Send an image URL or base64 data to a single endpoint. Describe images and get back tags, colors, faces, text, and NSFW scores from multiple AI models.
curl -X POST https://api.visionati.com/api/fetch \
-H "X-API-Key: Token YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com/image.jpg",
"backend": ["claude", "gemini", "googlevision"],
"feature": ["descriptions", "tags", "nsfw"],
"role": "general"
}'