Cerebrium vs Lambda Cloud

Cerebrium

Per-second GPU prices are public, a 94-operation OpenAPI spec covers the management API, and service account tokens expire and are limited to named projects. Deployed endpoints are callable without a token unless disable_auth = false is set, and no request rate limits, 429 handling or SLA were found in the reviewed documentation.

Lambda Cloud

H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated.

Cerebrium

1. Set disable_auth = false in cerebrium.toml before deploying. The default leaves the endpoint callable by anyone with the URL
2. Authenticate headless with CEREBRIUM_SERVICE_ACCOUNT_TOKEN. cerebrium login opens a browser
3. Raise response_grace_period for long work. It defaults to 15 minutes and async runs stop at 12 hours
4. Send ?async=true to get a run_id with HTTP 202, and add webhookEndpoint because async calls return no result to the caller
5. Check the plan before choosing hardware. A100, H100, H200, B200 and RTX PRO 6000 need Standard, and protected compute bills at twice the listed rate

Lambda Cloud

1. Call GET /instance-types first and read regions_with_capacity_available before trying to launch
2. Space launch calls 12 seconds apart; a sixth in a minute returns 429 with global/rate-limited
3. Branch on the error code, not the message or suggestion, which Lambda says may change
4. List instances before retrying a failed launch, since there's no idempotency key and a retry can start a second machine
5. Terminate the instance in a finally block; billing runs by the minute until you do