Image generation and editing
Use this route only for an image model returned to the current key. Start with one image and a default size; size, quality, count, reference images, and editing support can change both compatibility and the request-time charge.
Configure
bash
curl 'https://ai.tavonilo.com/v1/images/generations' \
-H "Authorization: Bearer $AI_SHOP_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model":"<IMAGE_MODEL_ID>","prompt":"A minimal product illustration","size":"1024x1024"}'- POST /v1/images/generations
- POST /v1/images/edits
- POST /v1/images/generations/async
- POST /v1/images/edits/async
- GET /v1/images/tasks/
Verify and recover
Check the key with /v1/models, make one small non-sensitive request, and retain only the timestamp, route, model, HTTP status, and request ID for support. A timeout does not prove a billable generation was not processed, so do not blindly replay long or image requests.
Security boundary
Use one key per device or workload. Never send an API key, auth.json, full private prompt, password, verification code, or payment data to support; revoke and replace a key immediately when exposure is suspected.