Generate structured item fields from the first three images
The API runs on your application instance. Schemas and field names come directly from the OpenAPI specification. Session-authenticated requests require a session on that instance.
bearerAuthAuthorizationBearer <inv_ token>id*stringuuidIdempotency-Key?stringUUID identifying one queue operation; safe to reuse for retries.
uuidX-Organization-ID?stringOrganization membership selected for this request. User-bound credentials may select any active membership; standalone tokens may only repeat their pinned organization ID.
uuidapplication/json- body
overwrite?booleantrueprompt?stringOptional replacement for the built-in inventory-analysis prompt. Omit it to use the server default.
length <= 5000Item enriched or completed response replayed
curl -X POST 'https://inventory.example.com/api/v1/resources/497f6eca-6276-4993-bfeb-53cbbbba6f08/analyze' \ -H 'Content-Type: application/json' \ -d '{}'Match one photographed object to existing inventory items POST
Requires direct inventory.read permission and the ai scope/ai.use permission. The uploaded image is transient and is not attached to an item. The server describes the dominant object, shortlists a bounded inventory catalog, and visually reranks up to five advisory matches. Clients must let the user review the result instead of treating it as an exact identifier.
Generate a square studio or transparent cover from an item image POST
Next Page