OpenAI API Error rate_limit_exceeded: Rate limit reached (TPM/RPM)

Warning↻ Retryable · exponential backoffHTTP 429 Too Many RequestsAI Provider

TL;DR · 10-second read

You exceeded requests or tokens per minute for this model. Retry after the suggested delay with backoff; read the x-ratelimit-* headers to pace requests.

Identify: does your log match?

What you see · exact log / response

{"error":{"message":"Rate limit reached for gpt-4o in organization org-XXXX on tokens per min (TPM): Limit 30000, Used 27410, Requested 4120. Please try again in 3.06s.","type":"tokens","param":null,"code":"rate_limit_exceeded"}}

Fix

Being written

Copy-paste fixes for rate_limit_exceeded are in the enrichment queue

The summary above is verified. Paste your full trace into the decoder for a diagnosis now.

Open the decoder →

Related errors

Last verified 2026-10-22 · Source: OpenAI error-code guide + SDK exception classes · Official docs ↗ · ~14,800 searches/mo