Document processing limits in IXP in Flow, covering field value, token, and page limits per model.

There is no fixed limit on the number of field values that IXP can extract per document. The limit depends on the extraction model.

If a document requires more field values than the model can return, the model may reach its token limit. This can happen even if the document is well within the page limits of the model. If you reach this limit, set the Extraction strategy to Advanced, if it is available to you, to handle more field values. For details, check Configuring the model.

If token limits are exceeded, predictions may be incomplete or empty regardless of the number of pages. For example, an 80-page document with 1,400 extracted field values may trigger a token-limit warning in the user interface. At runtime, when the token limit is exceeded, the API response will show this by returning occurrence and extraction confidence values of 0.

Page limits and token limits vary per model family and version. If a single model call reaches the page or token limit when you use the Standard extraction strategy, switch to the Advanced extraction strategy, if it is available to you. The Advanced strategy breaks documents into smaller, more manageable chunks for extraction.