Errors & Rate Limits

Error Format

All errors follow a consistent format:

{
  "error": {
    "code": "insufficient_balance",
    "message": "Your balance is too low to launch this instance. Please add credit.",
    "status": 402
  }
}

Error Codes

Code	HTTP Status	Description
`unauthorized`	401	Missing or invalid API key/token
`forbidden`	403	API key lacks required permission
`not_found`	404	Resource not found
`insufficient_balance`	402	Balance too low for operation
`validation_error`	422	Invalid request body
`gpu_unavailable`	409	Requested GPU not available
`provider_error`	502	Upstream provider error
`rate_limited`	429	Too many requests
`internal_error`	500	Internal server error

Rate Limits

Default: 60 requests per minute per API key
Configurable: Set per-key limits in the dashboard

Rate limit headers are included in every response:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1709312460

When rate limited, you’ll receive:

{
  "error": {
    "code": "rate_limited",
    "message": "Rate limit exceeded. Try again in 23 seconds.",
    "status": 429,
    "retry_after": 23
  }
}

Schedules PyTorch