---
metadata:
  - name: generator
    content: Diplodoc Platform v5.52.0
alternate:
  - https://catboost.ai/docs/en/concepts/input-data.md
  - href: en/concepts/input-data.md
    type: text/markdown
    title: Markdown version
  - href: ../llms.txt
    type: text/markdown
    title: llms.txt
---
> **Documentation Index:** Fetch the complete configuration index at https://catboost.ai/docs/en/llms.txt

# Input data

Input data for training, testing, and applying models can be passed as files containing:

- [Columns description](https://catboost.ai/docs/en/concepts/input-data_column-descfile.md)
- [Dataset in delimiter-separated values format](https://catboost.ai/docs/en/concepts/input-data_values-file.md)
- [Dataset in extended libsvm format](https://catboost.ai/docs/en/concepts/input-data_libsvm.md)
- [Pairs description](https://catboost.ai/docs/en/concepts/input-data_pairs-description.md)
- [Custom quantization borders and missing value modes](https://catboost.ai/docs/en/concepts/input-data_custom-borders.md)
- [Group weights](https://catboost.ai/docs/en/concepts/input-data_group-weights.md)
- [Baseline](https://catboost.ai/docs/en/concepts/input-data_baseline.md)

Non-CLI packages and libraries also support passing input data in data structures native to their languages.

{% note info %}

The data format is the same for training, testing, and applying models. Model application uses only features data.

{% endnote %}