🧠 LLM Parsing Models

Airparser allows you to select the parsing model for each Inbox independently. This means you can fine-tune the parsing performance for different document types without affecting other inboxes.

You can change the model at any time from the Inbox settings page.

Model comparison

Model Name	Speed	Document size	Description
Core-1	⭐️⭐️⭐️⭐️	⭐️⭐️⭐️	Default model for most use cases and document types. Balanced speed and accuracy.
Core-1.5	⭐️⭐️⭐️⭐️	⭐️⭐️⭐️	Variant of Core-1 that can perform better in certain edge cases.
Core-beta	⭐️⭐️⭐️	⭐️⭐️⭐️⭐️	Can process longer documents. Slower and best used only if other models fail.
Flex-1	⭐️⭐️⭐️	⭐️⭐️⭐️	Older stable model from the Flex family. Sometimes better for specific layouts.
Flex-1.5	⭐️⭐️⭐️	⭐️⭐️⭐️⭐️	Updated Flex model with longer document capacity.
Flex-beta	⭐️⭐️⭐️⭐️	⭐️⭐️⭐️⭐️	Latest Flex family model. Good for experimenting when Core models struggle.

What are parsing models?

Parsing models are the AI engines that process your documents and extract structured data. Airparser supports two families of advanced LLM-powered models:

Core family – our main, general-purpose models.
Flex family – alternative models that sometimes perform better for specific layouts or formats.

In many cases, the parsed output will be identical across models—especially within the same family.
However, results can vary slightly between families, as they use different approaches to document understanding.

Our default model, Core-1, covers most use cases and document types.
If it works well for your documents, we recommend keeping it.

Document size

Each model supports documents up to a certain length (measured in tokens, which roughly correspond to words and formatting).

Higher document size means the model can process longer documents.
However, keep in mind that longer processing can increase the risk of hallucinations—cases where the AI fabricates or misinterprets data.

For best accuracy, we recommend splitting very long documents into smaller sections whenever possible.

How to choose the right model

In most cases, Core-1 will be the best choice.
If parsing accuracy is not satisfactory, try models in the following order:

Core-1 (or Core-1.5)
Flex-beta
Flex-1.5 (or Flex-1)
Core-beta