Rate limit

[amber trench]

I receive this message when my claude subscription is maxed. I hoped it will fallback on my chatgpt account, but it's not. My config seams ok.

HTTP 429: rate_limit_error: This request would exceed your account's rate limit. Please try again later. (request_id: req_011CXaaeqVtep3vVgdpEj83N)

[echo marsh]

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

[hallow dagger]

The key insight is that Clawdbot's failover works in two stages:

1. Auth profile rotation within the same provider (e.g., if you have multiple Claude accounts, it tries the next one)
2. Model fallback to the next model in agents.defaults.model.fallbacks

A rate limit (429) causes Claude to enter cooldown, but it doesn't automatically switch to ChatGPT. The system will retry Claude after the cooldown expires.

To get ChatGPT as a true fallback, you need to configure it in your model fallbacks:

{
  agents: {
    defaults: {
      model: {
        primary: "anthropic/claude-opus-4-5",
        fallbacks: [

          "anthropic/claude-sonnet-4-5",
          "openai/gpt-5.2"  // ← ChatGPT fallback
        ]
      }
    }
  }
}

Then run:

clawdbot models fallbacks add openai/gpt-5.2

Check your current fallback config:

clawdbot models status

The docs: https://docs.moltbot.ai/concepts/model-failover

Does that match what you have configured? 🦐

[hallow dagger]

The key insight is that rate limits (429) don't automatically trigger provider fallback — Claude just enters cooldown and retries later. For true ChatGPT fallback on rate limits, you need to configure agents.defaults.model.fallbacks to include OpenAI models.

The docs explain the two-stage failover: https://docs.moltbot.ai/concepts/model-failover

Does your config have fallbacks set up?

[amber trench]

"agents": {
"defaults": {
"model": {
"primary": "anthropic/claude-opus-4-5"
},
"workspace": "/Users/gnarco/clawdbot_home",
"maxConcurrent": 4,
"subagents": {
"maxConcurrent": 8
}
},
"list": [
{
"id": "alfred",
"workspace": "/Users/gnarco/clawdbot_home",
"model": {
"primary": "anthropic/claude-opus-4-5",
"fallbacks": [
"openai-codex/gpt-5.2"
]
}
},
{
"id": "maison",
"workspace": "/Users/gnarco/clawdbot_home_maison",
"model": {
"primary": "anthropic/claude-opus-4-5",
"fallbacks": [
"openai-codex/gpt-5.2"
]
}
}
]
},

@hallow dagger

[hallow dagger]

What specifically would you like help with?

• Check your current config: Run clawdbot models status and share the output (redact any keys)
• Add ChatGPT fallback: clawdbot models fallbacks add openai/gpt-5.2
• Or something else?