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

# Protein Models API

> Run ESMC, ESMFold2, and ESM3 inference with HTTP requests.

The Protein Models API runs inference on ESMC, ESMFold2, and ESM3. For larger or longer-running workloads, use the [Batch API](https://docs.biohub.ai/api/protein/models/batch_overview.md).

## Install the esm package

To run `esm` locally, download the PyPI package. You can also call the API directly over HTTP without it, but the package provides a simpler way to access the API and additional useful libraries.

```bash theme={null}
pip install esm
```

To begin using the esm package, create an [API key](https://biohub.ai/developer-console/api-keys) and connect to the model you want to use:

```python theme={null}
from esm.sdk.forge import ESMCForgeInferenceClient

client = ESMCForgeInferenceClient(model="esmc-6b-2024-12", url="https://biohub.ai", token="<your API token>")
```

For ESMFold2 use `SequenceStructureForgeInferenceClient`, and for ESM3 use `ESM3ForgeInferenceClient`. See [Get started](https://docs.biohub.ai/learn/getting-started.md) for each model and [Tutorials](https://docs.biohub.ai/learn/tutorials/esmc) for code snippets that demonstrate how to use the `esm` SDK.

## Operations

| Operation | Models | Purpose |
| - | - | - |
| [fold](https://docs.biohub.ai/api/protein/models/fold.md) | ESM3, ESMFold2 | Fold proteins. Defaults to `esmfold2-fast-2026-05`. |
| [fold\_all\_atom](https://docs.biohub.ai/api/protein/models/fold_all_atom.md) | ESMFold2 | Fold molecular complexes containing proteins, DNA, RNA, and ligands. Defaults to `esmfold2-fast-2026-05`. |
| [logits](https://docs.biohub.ai/api/protein/models/logits.md) | ESM3, ESMC | Run one inference step and return logits, embeddings, and SAE features (ESMC only). |
| [encode](https://docs.biohub.ai/api/protein/models/encode.md) | ESM3, ESMC | Tokenize sequence, structure, or function annotations. |
| [decode](https://docs.biohub.ai/api/protein/models/decode.md) | ESM3, ESMC | Decode sequence, structure, or function annotation tokens. |
| [generate](https://docs.biohub.ai/api/protein/models/generate.md) | ESM3 | Generate an output track conditioned on inputs. |
| [generate\_tensor](https://docs.biohub.ai/api/protein/models/generate_tensor.md) | ESM3 | Generate an output track from raw tokens and return raw tokens. |
| [forward\_and\_sample](https://docs.biohub.ai/api/protein/models/forward_and_sample.md) | ESM3 | Run one inference step and sample output tokens. |
| [inverse\_fold](https://docs.biohub.ai/api/protein/models/inverse_fold.md) | ESM3 | Inverse fold proteins. Defaults to `esm3-open-2024-03`. |

## Example: send a request

Send a JSON body with `Content-Type: application/json` and authenticate with your API key:

```bash theme={null}
curl https://biohub.ai/api/v1/fold \
  -H "Authorization: Bearer $BIOHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "esmfold2-fast-2026-05",
    "sequence": "MKTAYIAKQRQISFVKSHFSRQLEERLGLIEVQ"
  }'
```

See each operation's page for its request fields and response schema.

## Response formats

Responses are JSON by default. Most operations also support Python pickle responses, which can reduce payload size for tensors and arrays. The `esm` Python SDK requests pickle automatically. See [Response formats](https://docs.biohub.ai/api/protein/models/response-formats.md).

## Input limits

On `fold` and `fold_all_atom`, ESMFold2 models accept inputs up to 768 tokens. For inputs up to 4096 tokens, or to run many predictions asynchronously, use [Batch folding](https://docs.biohub.ai/api/protein/models/batch_folding.md).

## On-demand or batch

| Use | When |
| - | - |
| Protein Models API | You need a result in the same request, for interactive or low-volume work. |
| [Batch API](https://docs.biohub.ai/api/protein/models/batch_overview.md) | You have many inputs, long inputs, or long-running jobs such as maximum-accuracy folding and binder design. |


## Related topics

- [Get started with ESM models](https://docs.biohub.ai/learn/getting-started.md)
- [ESM Atlas API](https://docs.biohub.ai/api/protein/atlas/overview.md)
- [fold](https://docs.biohub.ai/api/protein/models/fold.md)
- [ESMC](https://docs.biohub.ai/models/esmc.md)
- [ESM3](https://docs.biohub.ai/models/esm3.md)