Baseten vs Verda

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.

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.

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

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.