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

# Bunker Longevity Model Catalog: All Six Models

> Compare every Bunker Longevity AI model at a glance: category, parameters, version, and typical use case. Pick the right model for your task.

The Bunker Longevity catalog covers four life-science domains: protein structure, genomics, drug discovery, and imaging. Every model is served through the same API surface, so switching between them is a matter of changing the model name.

## Install

Every model in the catalog is accessible through the `bunker-fold` Python package:

```bash theme={null}
pip install bunker-fold
```

See [Installation](/installation) for full setup.

## All models

| Model                                  | Category       | Parameters | Version | Typical use                                                           |
| -------------------------------------- | -------------- | ---------- | ------- | --------------------------------------------------------------------- |
| [BunkerFold-3](/models/bunkerfold-3)   | Protein        | 1.2B       | v3.1    | Predict 3D structure from an amino acid sequence                      |
| [GenoScan-LLM](/models/genoscan-llm)   | Genomics       | 800M       | v2.0    | Whole-genome variant calling with clinical-grade sensitivity          |
| [MolGen-7](/models/molgen-7)           | Drug Discovery | 3.4B       | v7.0    | Generate small molecules optimized for a target                       |
| [CryoNet](/models/cryonet)             | Imaging        | 540M       | v1.4    | Reconstruct 3D density maps from cryo-EM micrographs                  |
| [ToxPredict-v2](/models/toxpredict-v2) | Drug Discovery | 280M       | v2.3    | Screen compounds for hepatotoxicity, cardiotoxicity, and mutagenicity |
| [EpiMark](/models/epimark)             | Genomics       | 420M       | v1.1    | Predict histone marks, methylation, and chromatin accessibility       |

## Pick by task

* **Predict a protein structure**: [BunkerFold-3](/models/bunkerfold-3) for sub-angstrom structure prediction with full side chains.
* **Call variants from a genome**: [GenoScan-LLM](/models/genoscan-llm) to flag pathogenic variants from BAM, CRAM, or VCF inputs.
* **Design a small molecule**: [MolGen-7](/models/molgen-7) to generate candidates against a specific target with ADMET constraints.
* **Reconstruct a cryo-EM map**: [CryoNet](/models/cryonet) to resolve 3D density maps with 10x fewer particles than standard pipelines.
* **Screen for toxicity**: [ToxPredict-v2](/models/toxpredict-v2) to filter compound libraries before synthesis.
* **Annotate the epigenome**: [EpiMark](/models/epimark) to predict histone marks and methylation from sequence context alone.

## Shared API surface

Every model uses the same three endpoints:

* `POST /v1/models/{model}/deploy` starts an inference instance.
* `POST /v1/models/{model}/predict` runs a prediction against a deployed instance.
* `GET /v1/models/{model}/status` reports deployment health and queue depth.

See the [API Reference](/api-reference/introduction) for full request and response schemas.