groq-rate-limits

# Groq Rate Limits ## Overview Handle Groq rate limits using the `retry-after` header, exponential backoff, and request queuing. Groq enforces limits at the organization level with both RPM (requests/minute) and TPM (tokens/minute) constraints -- hitting either one triggers a `429`. ## Rate Limit Structure Groq rate limits vary by plan and model. Limits are applied simultaneously -- you must stay under both RPM and TPM. | Constraint | Description | |-----------|-------------| | RPM | Requests per minute | | RPD | Requests per day | | TPM | Tokens per minute | | TPD | Tokens per day | Free tier limits are significantly lower than paid tier. Check your current limits at [console.groq.com/settings/limits](https://console.groq.com/settings/limits). ## Rate Limit Response Headers When Groq responds (even on success), it includes these headers: | Header | Description | |--------|-------------| | `x-ratelimit-limit-requests` | Max requests in current window | | `x-ratelimit-limit-tokens` | Max tokens in current window | | `x-ratelimit-remaining-requests` | Requests remaining before limit | | `x-ratelimit-remaining-tokens` | Tokens remaining before limit | | `x-ratelimit-reset-requests` | Time until request limit resets | | `x-ratelimit-reset-tokens` | Time until token limit resets | | `retry-after` | Seconds to wait (only on 429 responses) | ## Instructions ### Step 1: Parse Rate Limit Headers ```typescript import Groq from "groq-sdk"; interface RateLimitInfo { limitReque...