Deploy a Bunker Longevity Model Instance

Before you can send prediction requests to a Bunker Longevity model, you deploy an instance. Deploying reserves compute for your account and returns a deployment ID you can poll for readiness.

Deploy an instance

POST /v1/models/{model}/deploy

curl -X POST https://api.bunkerbio.com/v1/models/bunkerfold-3/deploy \
  -H "Authorization: Bearer $BUNKER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"instance_type": "gpu.a100", "replicas": 1}'

import requests, os

r = requests.post(
    "https://api.bunkerbio.com/v1/models/bunkerfold-3/deploy",
    headers={"Authorization": f"Bearer {os.environ['BUNKER_API_KEY']}"},
    json={"instance_type": "gpu.a100", "replicas": 1},
)
print(r.json())

Response

{
  "deployment_id": "dep_7f3a2c",
  "model": "bunkerfold-3",
  "status": "provisioning",
  "instance_type": "gpu.a100",
  "replicas": 1
}

Parameters

string

default:"gpu.a100"

Instance class. One of gpu.t4, gpu.a10, gpu.a100, gpu.h100.

integer

default:"1"

Number of replicas to deploy. Traffic is load-balanced across replicas.

integer

default:"30"

Automatically stop the instance after this many minutes of inactivity. Set 0 to disable.

Check deployment status

GET /v1/models/{model}/status

Poll status until it reports ready before sending prediction requests.

curl https://api.bunkerbio.com/v1/models/bunkerfold-3/status \
  -H "Authorization: Bearer $BUNKER_API_KEY"

Response

{
  "deployment_id": "dep_7f3a2c",
  "status": "ready",
  "replicas_ready": 1,
  "queue_depth": 0
}

string

Deployment status. One of provisioning, warming, ready, degraded, stopped.

integer

Number of prediction requests currently waiting in the queue.

Stop an instance

Release compute when you are done:

curl -X POST https://api.bunkerbio.com/v1/models/bunkerfold-3/stop \
  -H "Authorization: Bearer $BUNKER_API_KEY"

Instances are billed per second while they are in provisioning, warming, or ready states.

Get Started

Models

API Reference

Installation

Deploy a Bunker Longevity Model Instance

Deploy an instance

Parameters

Check deployment status

Stop an instance