Limits

Limits are set by the active deployment configuration; the API error text reports the current value. See errors for status codes and the migration checklist for request sizing.

state_too_long

Each question has its own state room: about 437–478 tokens with the English model's 512-token sequence, or 951–990 with the multilingual model's 1024-token sequence. Shorten the state or that question's instructions/options. See models.

instructions_too_long

Reduce the question's instructions or options.

request_too_large

Split the request. Processed tokens are questions multiplied by the longest sequence; the default ceiling is 3,500 for English or 6,000 for multilingual. The API error reports the selected worker's cap.

options_too_long

Shorten option names and descriptions. An option has a 48-token budget.

too_many_questions

Split the call; the default maximum is 32 questions.

rate_limited

The default account rate is 60 requests per minute. Honor Retry-After.

too_many_inflight

Wait for a running call to finish. The default account cap is two concurrent calls.

quota_tokens

The free monthly billed-input-token allowance is exhausted. See usage for the UTC reset time.

quota_compute

The internal compute allowance is exhausted. See usage for the UTC reset time.