#API CALLS/cooldown

1 messages · Page 1 of 1 (latest)

viscid tapir
#

⚠️ Agent failed before reply: All models failed (2): anthropic/claude-haiku-4-5-20251001: ⚠️ API rate limit reached. Please try again later. (rate_limit) | google/gemini-3-flash-preview: ⚠️ API rate limit reached. Please try again later. (rate_limit).
Logs: openclaw logs --follow

Not sure, what I am doing wrong, it's not connecting to my api and using it, i am just prompting my discord bot hello and get this message, tryna set up haiku primary and flash secondary. How long is the anthropic cooldown?

ripe sageBOT
#

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> âś… Mark Solution

sturdy moatBOT
#

That error actually means it is reaching your providers — both Anthropic and Gemini returned HTTP 429 / rate_limit, so OpenClaw tried:

  1. anthropic/…haiku… → got rate-limited
  2. fallback google/…flash… → also got rate-limited
    → so you see “All models failed”

How long is the Anthropic “cooldown”?

There isn’t one fixed cooldown time OpenClaw can tell you — it depends on your Anthropic account’s rate-limit window (often a per‑minute window, sometimes you’re effectively blocked until quota/billing/plan limits reset).

Practical answer:

  • If you just spiked it: try again after ~60–120s
  • If it keeps happening: check your Anthropic limits/usage/billing (or if you’re using a setup-token / subscription auth, you may need to wait for the provider window to reset or upgrade)

Docs (this exact situation):
https://docs.openclaw.ai/help/faq#why-am-i-seeing-http-429-ratelimiterror-from-anthropic

Quick debug checklist (to confirm it’s not misconfig)