🦞OpenClaw Guide
Models

Rate Limited — All Models Failed Cooldown

Your bot stops responding with 'all models failed' or provider cooldown errors.

⚠️ The Problem

Your bot was working fine, then suddenly stops responding with:

bash
Provider anthropic is in cooldown (all profiles unavailable) (rate_limit)All models failed (2): anthropic/claude-opus-4-5: No available auth profile

The cooldown can last from minutes to hours.

🔍 Why This Happens

You've hit the API rate limits for your provider. This happens when:

  1. Too many requests — Heavy usage exhausted your quota
  2. Large context — Sending huge prompts counts against limits faster
  3. Context overflow loop — A conversation got too long, causing repeated failures
  4. Multiple clients — Other apps using the same API key

✅ The Fix

Wait for the cooldown to expire (usually 15-60 minutes for Anthropic).

Check your current auth status:

bash
openclaw models status --probe

To prevent this in the future, add a fallback model:

json
{  "agents": {    "defaults": {      "model": {        "primary": "anthropic/claude-sonnet-4-5",        "fallback": ["openai/gpt-4o", "anthropic/claude-haiku-4-5"]      }    }  }}

Enable compaction to prevent context overflow:

bash
openclaw config set agents.defaults.compaction.mode safeguard

If you have heavy usage, consider adding multiple API keys (profiles).

🚀 Skip the setup. OpenClaw Cloud is ready in 60 seconds.

No server. No SSH. No config files. Just connect your channel and go.

Deploy Now — 50% Off First Month →

🔥 Your AI should run your business, not just answer questions.

We'll show you how.Free to join.

Join Vibe Combinator →

📋 Quick Commands

CommandDescription
openclaw models status --probeCheck model availability
/newStart a fresh session (in chat)
openclaw auth listView configured auth profiles

Related Issues

📚 You Might Also Like

Blog

OpenClaw Rate Limiting: How to Prevent a $500 Overnight Surprise (And Cap Your Monthly Bill)

## The $500 Overnight Surprise

Guide

How to Self-Host an LLM: Run AI Models on Your Own Hardware

Complete guide to running large language models locally. Llama, Mistral, Qwen, and other open-source models on your Mac, PC, or server — fully offline, zero API costs.

Integration

Linear

Modern project management through natural conversation. Create issues, track cycles, triage bugs, and run Linear queries — all without leaving your chat. Built for the speed-obsessed.

Comparison

OpenClaw vs Claude

Same brain, but it can actually do things

🐙 Your AI should run your business.

Weekly live builds + template vault. We'll show you how to make AI actually work.Free to join.

Join Vibe Combinator →