Tarseek API

Rate limits

Tarseek enforces project-level requests per minute (RPM), estimated tokens per minute (TPM), and concurrent-request limits before a provider receives the request. Launch defaults are 500 RPM, 500,000 TPM, and 25 concurrent requests per project; operators can change them per project, and API keys can have tighter overrides.

• HTTP 429 rate_limit_exceeded
• Headers: Retry-After, x-ratelimit-limit-requests, x-ratelimit-remaining-requests, and token equivalents
• Provider-side 429 failovers when another deployment exists; if none remain, Tarseek returns provider_rate_limit

Customer exhaustion returns HTTP 429 rate_limit_exceeded. Upstream capacity exhaustion first tries another eligible deployment.