---
title: "Create Compute Instance"
method: POST
path: "/compute/instances"
tags: ["Compute"]
---

# Create Compute Instance

`POST /compute/instances`

Creates a new compute instance with the specified configuration and SSH key.

**Requirements:**
- Requires compute permissions (extra_permissions.compute = true)
- Authentication required via admin API key
- Valid SSH public key required for instance access

**Key Features:**
- Create high-performance GPU instances
- Specify sector for InfiniBand configuration (8x H100 only)
- SSH key-based authentication
- Automatic instance provisioning and region assignment
- Idempotent creation with Idempotency-Key header (optional but recommended)

**Common Use Cases:**
- Spin up compute resources for ML training
- Create GPU instances for inference workloads
- Set up development environments with H100 GPUs
- Deploy distributed training with InfiniBand networking

**Instance Types:**
- `gpu_8x_h100_sxm5`: 8x NVIDIA H100 GPUs (high-performance, supports sector configuration for InfiniBand)
- `gpu_1x_h100_sxm5`: 1x NVIDIA H100 GPU (standard)

**Idempotency:**
- Optional Idempotency-Key header prevents duplicate instance creation on retries
- Responses cached for 10 minutes per unique key

See [fal.ai docs](https://fal.ai/docs/documentation/compute) for more details.

## Headers

- `Idempotency-Key` string — Optional idempotency key for safe request retries

## Request body

- object — Request body for creating a new compute instance with SSH access
  - `instance_type` 'gpu_8x_h100_sxm5' | 'gpu_1x_h100_sxm5', required — Type of compute instance to create
  - `ssh_key` string, required — SSH public key for accessing the instance (e.g., 'ssh-rsa AAAAB3...')
  - `sector` 'sector_1' | 'sector_2' | 'sector_3' — Sector for InfiniBand configuration (only valid with gpu_8x_h100_sxm5)

## Response `201`

Compute instance created successfully

- object — Compute instance details including configuration, location, and status
  - `id` string, required — Unique identifier for the compute instance
  - `instance_type` 'gpu_8x_h100_sxm5' | 'gpu_1x_h100_sxm5', required — Type of compute instance (GPU configuration)
  - `region` 'us-west' | 'us-central' | 'us-east' | 'eu-north' | 'eu-west' | 'other', required — Geographical region where the instance is located
  - `sector` 'sector_1' | 'sector_2' | 'sector_3' — Sector identifier for instance placement within the region (if applicable)
  - `ip` string — IP address of the instance (available when instance is ready)
  - `status` 'ready' | 'init' | 'pending' | 'provisioning' | 'stopped' | 'unknown', required — Current operational status of the instance
  - `creator_user_nickname` string — Nickname of the user who created this instance

## Other responses

- `400` — Invalid request parameters
- `401` — Authentication required
- `403` — Access denied
- `429` — Rate limit exceeded
- `500` — Internal server error

---

[API](https://skmtc.dev/fal/apis/platform-apis.md) · [All operations](https://skmtc.dev/fal/apis/platform-apis/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/fal/platform-apis/revisions/0c7dabf80b00/schema)