Limits and errors

Limits and errors

Errors use the OpenAI format, {"error": {"message", "type", "code"}}, with the status codes below.

Parallel requests

Each account runs up to 8 requests at once. A ninth waits up to 5 seconds for one to finish, then returns 429 concurrent_request_limit. Open a support ticket or talk to us to raise your limit.

Status codes

StatusCodeMeaning
400model_requiredThe request has no model, or its body is not valid JSON.
401invalid_api_keyThe API key is missing, wrong, or revoked.
402insufficient_creditsYour balance is too low. Top up and retry.
404model_not_foundThe model id is not one of the active models.
413request_too_largeThe request body is over 64 MiB.
429concurrent_request_limitYour account already has 8 requests running.
429rate_limited, rate_limit_exceededToo many requests. Wait for the Retry-After header, then retry.
503under_capacityThe model is temporarily unavailable. Retry shortly.

Retrying

Retry 429 after the Retry-After header and 503 after a short wait, with backoff. Don't retry 400, 401, 402, or 404; fix the request or the account first.

The OpenAI and Anthropic SDKs already retry 429 and 5xx with backoff. Raise their retries for agents that run many requests at once.

Python
client = OpenAI(
    base_url="https://api.silkcompute.com",
    api_key=os.environ["SILK_API_KEY"],
    max_retries=5,
)