> For the complete documentation index, see [llms.txt](https://docs.mindee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mindee.com/use-cases/extraction-models/boarding-pass.md).

# Boarding Pass

With Mindee, you can extract all the information needed for a passenger to access a flight: traveler identity, flight details, departure and arrival airports, and boarding information.

Here is how to build your custom Boarding Pass model with Mindee in just a few minutes:

{% @supademo/embed url="<https://app.supademo.com/demo/cmfl5e3l1erva39ozltfkx1ta>" demoId="cmfl5e3l1erva39ozltfkx1ta" %}

## Why use Mindee for boarding passes?

Boarding passes differ depending on airline, format (paper or mobile), and layout. Instead of handling these variations yourself, you can simply tell the AI Agent which fields you want to extract, and it will design the model for you.

Common use cases:

* Travel and mobility apps verifying passenger details
* Loyalty program enrollment and automation
* Expense reporting and travel management

### What can be extracted from boarding passes?

Typical fields you may want to capture include:

| Field                       | Description                                   |
| --------------------------- | --------------------------------------------- |
| Passenger Name              | Full name of the traveler                     |
| Flight Number               | Airline code and flight number                |
| Departure Date              | Date of departure in YYYY-MM-DD               |
| Boarding Time               | Boarding time                                 |
| Departure Airport           | Name and IATA code of the origin airport      |
| Destination Airport         | Name and IATA code of the destination airport |
| Bardcode (Object Detection) | Image of the barcode                          |

Depending on your needs, you can also add fields such as **Seat Number**, **Gate**, or **Booking Reference (PNR)**.

Here is a boarding pass sample if you want to try a live test for your model:

<figure><img src="https://4029869281-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fu5bStlX8nv4b9z4GXB2S%2Fuploads%2Fgit-blob-bbcf7660b5dff2031143e780dd656a44e46335dc%2Fboarding-pass-sample.jpg?alt=media" alt="a fake boarding pass"><figcaption></figcaption></figure>

## How to Create your Boarding Pass Model

Since there is no boarding pass Model Template in the Catalog, you will need to build your own custom model using the AI Agent:

1. Describe what you want to the AI assistant (e.g. *“I want to capture passenger name, flight number, departure date, and airports from boarding passes. Also add an object detection field for the barcode zone.”*)
2. Optionally upload a sample boarding pass to give more context.
3. The Agent will generate a model for you and propose a set of fields.
4. You can refine the schema by asking for more or fewer fields until it matches your requirements.
5. Once ready, you can test the model live with your documents.

## Document format support

The custom model accepts PDF and common image formats (JPG, PNG). It works with digital boarding passes as well as photos or scans of printed passes. See full [list of accepted files](https://docs.mindee.com/integrations/technical-limitations#accepted-files).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.mindee.com/use-cases/extraction-models/boarding-pass.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.