SSH Keys

The SSH Keys API lets you upload and manage public SSH keys used to authenticate with your GPU deployments. You must upload at least one SSH key before you can deploy a GPU cluster — keys are injected into the instance at provisioning time.

Base URL: https://gpu.huddleapis.com/api/v1

Prerequisites

You need an SSH key pair on your local machine. If you don't have one:

# Generate an Ed25519 key (recommended)
ssh-keygen -t ed25519 -C "your-email@example.com"

# Or generate an RSA key
ssh-keygen -t rsa -b 4096 -C "your-email@example.com"

Your public key is typically at ~/.ssh/id_ed25519.pub or ~/.ssh/id_rsa.pub.

Upload a Key

curl -X POST -H "X-API-Key: mk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-laptop",
    "public_key": "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIG... user@laptop"
  }' \
  https://gpu.huddleapis.com/api/v1/ssh-keys

Response:

{
  "code": "OK",
  "data": {
    "id": "sk_abc123",
    "name": "my-laptop",
    "fingerprint": "SHA256:xYz1234567890abcdefghijklmnop",
    "key_type": "ed25519",
    "created_at": "2026-04-03T10:00:00Z"
  }
}

Supported Key Types

Type	Recommendation
`ed25519`	Recommended — modern, fast, secure
`rsa`	Widely supported — use 4096-bit minimum
`ecdsa`	Supported — less common

List Your Keys

curl -H "X-API-Key: mk_your_key" \
  https://gpu.huddleapis.com/api/v1/ssh-keys

Response:

{
  "code": "OK",
  "data": [
    {
      "id": "sk_abc123",
      "name": "my-laptop",
      "fingerprint": "SHA256:xYz1234567890abcdefghijklmnop",
      "key_type": "ed25519",
      "created_at": "2026-04-03T10:00:00Z"
    }
  ]
}

Delete a Key

curl -X DELETE -H "X-API-Key: mk_your_key" \
  https://gpu.huddleapis.com/api/v1/ssh-keys/sk_abc123

Existing deployments are unaffected

Deleting an SSH key does not remove it from deployments that are already running. It only prevents the key from being used in future deployments.

Using Keys in Deployments

Pass one or more SSH key IDs when creating a deployment:

curl -X POST -H "X-API-Key: mk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "cluster_type": "1H100.80S.30V",
    "image": "ubuntu-22.04-cuda-12.4-cluster",
    "hostname": "my-gpu",
    "ssh_key_ids": ["sk_abc123", "sk_def456"],
    "location": "FIN-01"
  }' \
  https://gpu.huddleapis.com/api/v1/deployments/clusters

Once the deployment reaches running status, SSH in using the IP from the deployment response:

ssh root@<deployment_ip>

Next Steps

Ready to deploy? See the Deployments guide
Need an API key first? Visit API Keys