Our API maintains 99.9% uptime with rate limits of 10 requests per second (20 in bursts).
Common AI issues include incorrect API keys, low usage tier limits, and rate limiting. For OpenAI integrations, you need 30,000 TPM for content generation and 450,000 TPM for Claygent - tier 1 plans won't support these requirements.
We're deploying features like retries and smarter pacing to reduce rate limit errors and improve stability.
Are you experiencing specific error messages or issues with particular AI features?
Hi William, thank you for your question. I’m happy to check this for you. Just to confirm, are you referring to the AI action enrichment or to connecting your OpenAI account to Clay?