Beam vs Nebius AI Cloud

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.

Nebius AI Cloud

One API definition generates the REST and gRPC interfaces, the CLI, Terraform provider and three SDKs, with a 602-operation OpenAPI document, X-Idempotency-Key and role-scoped service accounts. The status page lists 14 major incidents between 14 July and 8 October 2026, no request rate limits were found, and signup needs a browser and a card.

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

Nebius AI Cloud

1. Use a service account with an authorised key, then exchange a five-minute RS256 JWT at https://auth.eu.nebius.com/oauth2/token/exchange for a 12-hour Bearer token
2. Send X-Idempotency-Key with a random UUID on every create, update and delete, since a 504 can follow a call that succeeded
3. Poll the returned operation (/ai/v1/endpoints/operations/{id}) until status is set; concurrent operations on one resource are not supported
4. Stop or delete endpoints when idle. A stopped endpoint bills nothing, a stopped Devlab or VM still bills for its disk
5. Check region support first. Serverless AI is absent from eu-south1 and us-north1, and each GPU platform exists in one to four regions
6. Run the beta nebius/mcp-server with safe mode on (the default); nebius_cli_execute can run any CLI command when SAFE_MODE=false