Error Codes

SeedofCode AI uses standard HTTP status codes to indicate the success or failure of an API request. In general:

• 2xx indicates success.
• 4xx indicates an error that failed given the information provided (e.g., missing API key, insufficient credits).
• 5xx indicates an error on our servers.

When an error occurs, the response body will contain a JSON object with an error message detailing what went wrong.

{
  "error": "Insufficient credits or wallet not found",
  "statusCode": 402,
  "message": "Payment Required"
}

Common Status Codes

400 Bad Request

The request was improperly formatted, missing required parameters, or requested a model that does not exist or is currently disabled. Example: You requested model: "gpt-4" which we do not host.

401 Unauthorized

The API key is missing, invalid, or has been revoked. Ensure you are sending the key in the x-api-key: <key> header and that the key starts with soc_live_.

402 Payment Required

Your wallet has insufficient credits to complete the requested inference. Because SeedofCode AI is a pay-per-token platform, we calculate the maximum possible cost of your request (Prompt Tokens + max_tokens limit) before generating. If your balance is lower than this maximum estimated cost, the request is rejected with a 402. Top up your credits in the dashboard to continue.

429 Too Many Requests

You have exceeded your rate limit. Wait a moment before retrying your request. If you need higher throughput, please contact support to have your limits raised.

502 Bad Gateway

The underlying inference node (Ollama) failed to generate a response, or the worker queue timed out. This is typically a transient error. You are not charged for requests that result in a 5xx error. You may safely retry the request.