Beam vs Hyperbolic

Beam

Per-millisecond billing with cold starts and image pulls free, H100 PCIe at $3.50 and RTX 4090 at $0.69 an hour. No published request rate limits, 429 handling or SLA.

Hyperbolic

The API serves its own OpenAPI 3.1 document without a key, lists GPU prices on an open endpoint and dates the removal of legacy paths at 1 March 2027. API keys carry no scopes and can delete the account, rental creation has no idempotency key, and renting needs a browser signup and a $5 deposit.

Beam

1. Check the response body for ok: false on gateway calls; a failure can arrive as HTTP 200
2. Don't pipe beam deploy --format json output into CI logs, since it contains the workspace token
3. Route anything over 180 seconds to a task queue and poll the task instead of holding the endpoint request
4. Set keep_warm_seconds deliberately; the 180-second endpoint default bills three minutes of GPU after every call
5. Pass gpu=["RTX4090", "A10G"] so a job still schedules when one type is out

Hyperbolic

1. Read GET /v2/on-demand/rental-options first. It needs no key and lists what can be rented now, with costPerHourCents per GPU configuration.
2. Send rentalType and gpuCount to POST /v2/on-demand/rentals. Region defaults to us-central-1 and GPU type to h100, so set both from the options list.
3. List active rentals before retrying a failed create call. There is no idempotency key and every ready rental bills hourly.
4. Save an SSH public key with POST /v2/ssh-keys before renting. Without sshPublicKeyIds the newest saved key is attached.
5. Do not create reserved rentals unless asked. They are paid in full up front and cannot be terminated early.