Classification resource that can later be retrieved via GET /v1/classifications/{classification_id} or listed via GET /v1/classifications.
Category has a name and optional description.16.true, bypass the cache and re-run the classification.id, filename, mime_type.choices, likelihood).The document to classify
The categories to classify the document into
The model to use for classification
Only use the first N pages of the document for classification. Useful for large documents where classification can be determined from early pages.
Additional context for classification (e.g., iteration context from a loop)
Number of classification runs to use for consensus voting. Uses deterministic single-pass when set to 1.
1 <= x <= 16If true, skip the LLM cache and force a fresh completion
Successful Response
Backend-internal classification with organization scoping.
Information about the classified file
Model used for classification
Categories the document was classified against
The classification result with reasoning
Organization ID of the user or application
Unique identifier of the classification
Number of consensus votes used
Additional context supplied with the classification request
Consensus metadata for multi-vote classification runs
Usage information for the classification