Massed Compute vs Modal

Massed Compute

The hosted MCP server and REST API accept OAuth grants or API tokens in read-only and full-access tiers, and all 17 tools carry typed schemas and safety annotations in a public server card. No status page, rate limit figures or API changelog were found, a launch has no idempotency key, and the governing terms could not be read.

Modal

Scale to zero by default, per-second billing and about one-second container boots. No REST API or OpenAPI spec for deploying or invoking Functions.

Massed Compute

1. Use https://vm.massedcompute.com/api/v1. The older docs at api-docs.massedcompute.com describe a separate marketplace API on api.massedcompute.com whose keys come from support.
2. Ask the owner for a read-only token unless the task must launch or terminate. Read-only credentials cannot call launch, restart, terminate or SSH key changes.
3. Call gpu_inventory_list and images_list before instances_launch. Product names and image IDs are free values, and SXM-only images do not run on PCIe cards.
4. Expect 402 on launch until the owner has added credit and set a recharge amount and threshold. List instances before retrying a launch.
5. Terminate to end billing. Stopping keeps the full hourly charge, and termination deletes the instance data.

Modal

1. Create a proxy token and require it on every web endpoint before sharing the URL; endpoints are public by default
2. Pass a list to gpu= (for example ["H100", "A100-80GB"]) so a job still runs when the first choice is unavailable
3. Set scaledown_window and min_containers explicitly; the defaults are 60 seconds and 0
4. Use .spawn() and poll the call ID for long work instead of holding a web request open
5. Keep web endpoint traffic under 200 requests a second or ask Modal to raise the limit