Baseten vs Crusoe Cloud

Baseten

Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.

Crusoe Cloud

The v1 REST API has a published OpenAPI description, Markdown docs, HMAC-signed keys, reader roles and a 90-day audit log, with on-demand GPU prices public. No idempotency keys or control-plane rate limits were found, spot and B200 prices go through sales, and a storage outage in eu-norway1 lasted about four hours on 29 September 2026.

Baseten

1. Create a team key with inference-only permission for calling models and keep full-access keys out of the agent
2. Sleep for retry_after seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute
3. Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code
4. Set scale_down_delay below the 900-second default or every burst bills 15 idle minutes
5. Send payloads over 256 KiB to /predict, not /async_predict, unless support has raised the async limit

Crusoe Cloud

1. Sign every request. Build the payload from path, sorted query string, verb and X-Crusoe-Timestamp, HMAC-SHA256 it with the base64url-decoded secret, and send Authorization: Bearer 1.0:<access_key_id>:<signature>.
2. Use https://api.cloud.crusoe.ai/v1. Some docs pages and the MCP server still name api.crusoecloud.com and /v1alpha5.
3. Creates, updates and deletes return an operation. Poll the matching operations endpoint for state, and list existing resources by name before retrying a create, because no idempotency key was found.
4. Managed AI uses separate Intelligence API keys and hosts, api.inference.crusoecloud.com for OpenAI-compatible calls and api.intelligence.crusoecloud.com for files and fine-tuning jobs.
5. Delete a VM and its disks to stop charges. A stopped on-demand VM is not billed for compute, but its 128 GB OS disk still bills at $0.08 a GiB-month.