Vision

AI Vision Analysis — verging.ai

Analyze images using GPT-4o Vision through the verging.ai proxy API. Supports both image URL and file upload.

Authentication

All requests require an API key in the Authorization header:

Authorization: ApiKey vrg_sk_xxx

Replace vrg_sk_xxx with your verging.ai API key. You can generate one at https://verging.ai under your account settings.

Endpoints

Option A — Image URL (JSON)

POST https://verging.ai/api/v1/ai/vision
Content-Type: application/json

Option B — File Upload (multipart)

POST https://verging.ai/api/v1/ai/vision/upload
Content-Type: multipart/form-data

Parameters

JSON (URL mode)

Multipart (file upload mode)

Requires a minimum balance of 5 credits before calling (post-deduct billing).

Examples

Image URL

curl -X POST https://verging.ai/api/v1/ai/vision \
  -H "Authorization: ApiKey vrg_sk_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Describe what you see in this image in detail.",
    "image_url": "https://example.com/photo.jpg",
    "max_tokens": 512
  }'

File Upload

curl -X POST https://verging.ai/api/v1/ai/vision/upload \
  -H "Authorization: ApiKey vrg_sk_xxx" \
  -F "prompt=What objects are in this image?" \
  -F "file=@photo.jpg"

Response

{
  "content": "The image shows a modern office space with several desks...",
  "usage": {
    "prompt_tokens": 1100,
    "completion_tokens": 95,
    "total_tokens": 1195
  },
  "credits_consumed": 2
}

• content — The analysis result text.
• usage — Token usage breakdown.
• credits_consumed — Credits deducted for this request.

Credits

Minimum charge: 2 credits per request.

Error Codes

Error response format:

{
  "error_code": 40001,
  "message": "Insufficient credits. Required: 5, available: 2",
  "upstream_error": null
}