AINewsnow

OpenAI max_retries=2 Turned 6 Attempts Into 18 Requests

This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.

The openai Python SDK already retries a 429 twice by default, so the tenacity decorator from OpenAI's own rate-limit cookbook, stop_after_attempt(6) , sent 18 requests per call to my test server, not 6. Pick one retry layer: either OpenAI(max_retries=0) under a tenacity policy that only retries err…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-16 05:41 · DEV Community — AI
    OpenAI max_retries=2 Turned 6 Attempts Into 18 Requests

More stories

  1. ChatGPT, Claude, Gemini and Grok helped plan terror attacks in US government test — The Independent Tech
  2. OpenAI unveils Performance Factory, a Codex-powered system that keeps ChatGPT fast — OpenAI News
  3. Developers increasingly run Claude Code alongside rival coding agents and alternative backends — DEV Community — AI
  4. Perplexity Launches Orchestrator API With Same-Model Failover — Unite.AI
  5. AI Coding Agents Face Growing Scrutiny Over Security, Performance and Workflow Integration — Forbes AI
  6. California lawsuit against OpenAI raises question of legal accountability for AI actions — New Scientist Technology
  7. OpenAI builds Performance Factory using Codex agents to keep ChatGPT fast — OpenAI (X)
  8. Palo Alto Networks to Acquire AI Startup Applied Compute for $4.5 Billion in Stock — Techmeme

Read the Daily Brief: the day's most important AI stories →