does the moderation endpoint have a rate limit?
#does the moderation endpoint have a rate limit?
opal mist
median nymphBOT
Hi @opal mist. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Yes, the moderation endpoint does have a rate limit. As per the forum post (https://community.openai.com/t/566911), the free plan allows for 3 requests per minute. If you need a higher rate limit, you can upgrade to a paid plan. For instance, paying at least $5 can get you to usage tier 1, which allows for 500 requests per minute (RPM).
However, it's important to note that while the moderation endpoint is free to use for monitoring the inputs and outputs of OpenAI APIs, its usage does not count towards your monthly usage limits as stated in this help article (https://help.openai.com/en/articles/4936833-are-the-moderation-endpoint-and-content-filter-free-to-use).
Rate limits are measured in five ways: RPM (requests per minute), RPD (requests per day), TPM (tokens per minute), TPD (tokens per day), and IPM (images per minute). These limits are imposed at the organization level, not the user level, and they vary by the model being used. You can learn more about rate limits in the OpenAI documentation (https://platform.openai.com/docs/guides/rate-limits?context=tier-free).
If you exceed these limits, you may encounter error messages such as 429: 'Too Many Requests' or RateLimitError. You can find tips for avoiding and handling rate limit errors in this guide (https://cookbook.openai.com/examples/how_to_handle_rate_limits).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
ancient zenith
@median nymph Whats the rate limit on tier 2
median nymphBOT
Let me check the knowledge base for you. One moment! :books:
The rate limit for Tier 2, according to the OpenAI documentation (https://platform.openai.com/docs/guides/rate-limits?context=tier-free), is set at a usage limit of $500 per month. To qualify for Tier 2, you must have paid $50 and it must be 7+ days since your first successful payment.
However, the exact rate limits in terms of requests per minute (RPM), requests per day (RPD), tokens per minute (TPM), tokens per day (TPD), and images per minute (IPM) can vary depending on the specific model you are using. For instance, the gpt-3.5-turbo model has a limit of 3 RPM and 40,000 TPM on the free tier, but these limits may be higher on Tier 2.