> ## Documentation Index
> Fetch the complete documentation index at: https://docs.synthesize.bio/llms.txt
> Use this file to discover all available pages before exploring further.

# Available metadata

> Browse and download the metadata vocabularies that each Synthesize Bio model accepts.

Every model on Synthesize Bio accepts a specific set of metadata fields as inputs — things like cell type, tissue, disease state, and perturbation details. The valid values for each field (e.g. ontology IDs, cell line names) are defined by the model's vocabulary.

The vocabulary depends on the **model** you're using, since different model versions and modalities (bulk vs. single-cell) accept different fields and values.

## Browse vocabularies on the platform

You can browse and download the vocabulary for any model you have access to at:

<Card title="app.synthesize.bio/docs/vocab" icon="book" href="https://app.synthesize.bio/docs/vocab">
  Pick a model from the dropdown to see every metadata field it accepts, with downloadable JSON files of the valid values.
</Card>

Each field links to a JSON file containing the full list of valid values. Use these lists to validate inputs before you submit a query, or to discover which ontology IDs / cell lines / tissues are supported for a given model.

## From the SDKs

Both SDKs let you discover models programmatically with `list_models()`. Once you have a `model_id`, head to the [vocabulary browser](https://app.synthesize.bio/docs/vocab) to see exactly which metadata that model accepts.

<CardGroup cols={2}>
  <Card title="Python: pysynthbio" icon="python" iconType="brands" href="/pysynthbio/getting-started">
    `list_models()` and `get_example_query(model_id=...)`
  </Card>

  <Card title="R: rsynthbio" icon="r-project" iconType="brands" href="/rsynthbio/getting-started">
    `list_models()` and `get_example_query(model_id = ...)`
  </Card>
</CardGroup>

## Next article

<Card title="Public dataset preprocessing" icon="filter" href="/get-started/data-preprocessing">
  Learn how public RNA-seq datasets are sourced, processed, and quality-checked.
</Card>