API referenceDocumentation

Errors & limits

Status codes, retry guidance, and platform limits.

On this page

Standard OpenAI-style error responses:

Status	Meaning	Retry?
`401`	Missing or invalid API key	no — fix the key
`400`	Malformed request or unsupported parameter	no — fix the request
`402`	Your prepaid balance (or $1 trial credit) is used up. The message includes a billing link	no — top up, then retry
`403`	This key reached the spending limit set on it	no — raise the key limit or use another key
`429`	Edge, per-key, or provider rate limit, or a rolling-window key budget	yes, with backoff
`5xx`	Upstream provider issue	yes

Error bodies follow the OpenAI shape:

json

{
  "error": {
    "message": "...",
    "type": "invalid_request_error",
    "code": "..."
  }
}

When a request is rejected by a key budget or your available balance, read the returned error.message and error.code before retrying. A retry cannot raise a hard budget or restore a zero balance. Top up (402) or raise the key limit (403) first.

Platform limits #

Requests are limited to 60/s per IP at the edge. This is separate from optional per-key RPM/TPM limits and the tighter limits on promotional accounts.
Request bodies up to 50 MB (plenty for base64 vision payloads).
Streams stay open for up to 10 minutes.