🖼️✨
Chat with any image

Upload a photo and ask questions about it. The AI will describe, analyze, and explain anything in your image.

1
Upload an image from the sidebar or below
2
Type any question about the image
3
Continue the conversation with follow-ups
image.jpg
Base URL

Single endpoint. CORS enabled for all origins. No authentication required.

Endpoint
POST/api/chat

Send an image and a question. The AI analyzes the image and returns a natural language response. Supports multi-turn conversations by passing previous messages.

FieldTypeStatusDescription
imagestringrequiredBase64 data URL — data:image/jpeg;base64,...
userPromptstringrequiredThe question or instruction about the image
messagesarrayoptionalPrevious turns for multi-turn chat. Each item: { type: "user"|"ai", content: "..." }
CURL

          
JAVASCRIPT

          
RESPONSE
{ "success": true, "response": "The image shows a golden retriever..." }
Multi-turn example
JAVASCRIPT

      
Image encoding helper
JAVASCRIPT
// File input → base64 data URL
function fileToBase64(file) {
  return new Promise((resolve, reject) => {
    const reader = new FileReader();
    reader.onload  = () => resolve(reader.result);
    reader.onerror = reject;
    reader.readAsDataURL(file);
  });
}

// Usage
const file    = document.querySelector('input[type=file]').files[0];
const dataUrl = await fileToBase64(file);
// dataUrl === "data:image/jpeg;base64,/9j/4AAQ..."
Error codes
400
Missing image or userPrompt, or invalid image format
413
Image too large for the AI service
429
Rate limited — wait and retry
502
Upstream AI service error
405
Method not allowed — use POST only
Notes
• Image must be a data:image/... base64 data URL — not a raw URL or blob URL.
• Supported types: JPEG, PNG, WEBP, GIF.
• Max recommended image size: ~10MB before encoding.
• For multi-turn chat, pass the full messages history on every request.
• The messages array should contain all previous turns in order.
VisionChat APIREST · v1 · Free
Base URL
GET/api/imgchatjson

Health check — confirms the service is running.

Click Open → see live response in your browser
Open
POST/api/imgchatjson

Send an image + question, get an AI answer. Supports OCR, object detection, text extraction, multi-turn chat.

ParamTypeDescription
userPromptstringrequiredYour question about the image.
imagestringoptionalBase64 image data (use this OR url).
urlstringoptionalPublic image URL (use this OR image).
messagesarrayoptionalPrior turns for multi-turn chat.
Copy & run in your terminal
curl -X POST {ORIGIN}/api/imgchat \
  -H "Content-Type: application/json" \
  -d '{"url":"https://picsum.photos/400","userPrompt":"What is in this image?"}'
POST endpoints can't be opened by clicking a URL — paste the curl above into your terminal, or call it with fetch() in code.