> ## 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 API: Deploy Models and Run Inference

> The Bunker Longevity API exposes every model through a uniform surface: deploy an instance, run inference, and check status. Bearer token auth over HTTPS.

The Bunker Longevity API exposes every model through a uniform REST surface. You deploy an instance, send a prediction request, and receive JSON back. The same three endpoints work for every model in the [catalog](/models/overview).

## Base URL

```text theme={null}
https://api.bunkerbio.com/v1
```

All requests must use HTTPS. HTTP requests are rejected.

## Authentication

Every request must include a bearer token in the `Authorization` header.

```bash theme={null}
curl https://api.bunkerbio.com/v1/models \
  -H "Authorization: Bearer $BUNKER_API_KEY"
```

See [Authentication](/authentication) for how to generate keys, choose scopes, and rotate credentials.

## Endpoints

| Method | Path                         | Description                                   |
| ------ | ---------------------------- | --------------------------------------------- |
| `GET`  | `/v1/models`                 | List all available models                     |
| `POST` | `/v1/models/{model}/deploy`  | Start an inference instance for a model       |
| `POST` | `/v1/models/{model}/predict` | Run a prediction on a deployed model          |
| `GET`  | `/v1/models/{model}/status`  | Report deployment health and queue depth      |
| `POST` | `/v1/models/{model}/stop`    | Stop a running instance and release resources |

See [Deploy a model](/api-reference/deploy) and [Run inference](/api-reference/inference) for full request and response schemas.

## Content type

All request bodies must be JSON with `Content-Type: application/json`. Responses are always JSON, including error responses.

## Rate limits

Rate limits are applied per API key. You can inspect current usage in the response headers of any successful call:

| Header                  | Meaning                                  |
| ----------------------- | ---------------------------------------- |
| `X-RateLimit-Limit`     | Requests allowed per minute              |
| `X-RateLimit-Remaining` | Requests remaining in the current window |
| `X-RateLimit-Reset`     | Unix timestamp when the window resets    |

When you exceed the limit, the API returns `429 Too Many Requests`. Retry with exponential backoff.

## Errors

Errors return a JSON body with a `code` and `message`. See [Errors](/api-reference/errors) for the full list of error codes.

```json theme={null}
{
  "error": {
    "code": "invalid_sequence",
    "message": "Sequence contains characters outside the IUPAC amino acid set"
  }
}
```