Cerebrium vs Verda

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.

Verda

The REST API has a public OpenAPI 3.1 document, a dated changelog, published rate limits with Retry-After, and an audit log endpoint. The CLI's MCP server refuses billed or destructive calls without confirm: true. Access needs a browser signup and a prepaid balance, credentials carry one scope, and instance creation has no idempotency key.

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

Verda

1. Exchange the client ID and secret at POST /v1/oauth2/token, then send the access token as a Bearer header. It expires after 3,600 seconds, so refresh it.
2. Send location_code on every create call. Requests without it have returned 400 since March 2026.
3. Call GET /v1/instance-availability before launching. POST /v1/instances returns 503 service_unavailable when the location has no capacity.
4. List instances before retrying a failed launch, because create has no idempotency key.
5. Use the delete action to stop charges. shutdown keeps billing, and deleted volumes stay recoverable for 96 hours unless delete_permanently is set.