App

Errors and how to recover

Every error is JSON with a detail field. Where there is something to act on, detail is an object with the specifics.

StatusWhenWhat to do
400A request is invalid, for example no requested GPU model exists in the fleet.Read detail. For GPUs, detail.available lists the ids you can use.
401The API key is missing or wrong.Send Authorization: Bearer <key>. Create a key under Settings.
402Your balance is below one hour of the rental's price.Top up on Billing. detail gives the exact amounts.
403Your key can't access that resource.Use a key from the account that owns it.
404The deployment or workload doesn't exist, or isn't yours. On /ssh, the pod isn't ready yet.Check the id; for /ssh, wait for state: "ready".
409The action conflicts with the current state, for example resuming a pod whose machine is full.Read detail; for resume, try again later or start a new rental.
422The request body doesn't match the schema.detail lists each bad field and why.
429Rate limit (30 creates per minute per key).Wait and retry with back-off.

The two you will see most

400 — GPU not available

{
  "detail": {
    "message": "none of the requested GPU models are available to rent",
    "requested": ["h100"],
    "available": ["rtx4090", "rtx5090"],
    "hint": "set supported_gpu_models to one of `available` (any spelling); see GET /platform/pricing"
  }
}

This is returned immediately when you start the deployment, so you never wait on a rental that could never be placed.

402 — not enough balance

{
  "detail": {
    "message": "insufficient balance to start this rental",
    "required_cents": 40,
    "current_cents": 12,
    "rate_cents_per_hour": 40,
    "gpu_count": 1,
    "requested_instances": 1
  }
}

You need required_cents - current_cents more, here $0.28. Top up, then retry the same request.

A deployment that ends up failed

Read last_error on GET /platform/deployments/{id}. The most common causes:

  • The image doesn't exist or is private. Check the image name; only public images can be pulled.
  • The image's CUDA is too old for an RTX 5090. Use a CUDA 12.8+ image (see GPU rental).

A failed deployment is not billed.

View as Markdown