openclaw - 💡(How to fix) Fix Windows QuickStart defaults first chat to paid Anthropic model without credit warning

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

On Windows QuickStart onboarding, the first chat can fail immediately because the flow defaults to an expensive Anthropic model without warning that API credits are required.

This makes a successful install look broken to a new user.

Error Message

run error: LLM request rejected: Your credit balance is too low to access the Anthropic API. Please go to Plans & Billing to upgrade or purchase credits.

Root Cause

On Windows QuickStart onboarding, the first chat can fail immediately because the flow defaults to an expensive Anthropic model without warning that API credits are required.

Code Example

iwr -useb https://openclaw.ai/install.ps1 | iex

---

run error: LLM request rejected: Your credit balance is too low to access the Anthropic API. Please go to Plans & Billing to upgrade or purchase credits.

---

[gateway] agent model: anthropic/claude-opus-4-7
RAW_BUFFERClick to expand / collapse

Summary

On Windows QuickStart onboarding, the first chat can fail immediately because the flow defaults to an expensive Anthropic model without warning that API credits are required.

This makes a successful install look broken to a new user.

Environment

  • OS: Windows 11 Version 25H2
  • OpenClaw: 2026.5.27 (27ae826)
  • Node: v24.16.0
  • Install method: PowerShell install script / QuickStart
  • Terminal: Windows PowerShell
  • Provider selected during onboarding: Anthropic

Steps to reproduce

  1. Run the Windows PowerShell install script as administrator:
    iwr -useb https://openclaw.ai/install.ps1 | iex
  2. Complete onboarding using QuickStart mode.
  3. Select Anthropic as provider.
  4. Select "Hatch in Terminal" at the final onboarding step.
  5. Observe the first automated/bootstrap message sent to the agent.

Expected result

The first chat milestone should either:

  • succeed with the configured provider/model, or
  • warn before setup completion that the selected/default model requires paid credits and may fail without billing enabled.

If a paid/high-cost model is selected, the user should get a clear preflight warning before onboarding finishes.

Actual result

The first chat failed immediately with:

run error: LLM request rejected: Your credit balance is too low to access the Anthropic API. Please go to Plans & Billing to upgrade or purchase credits.

Gateway output showed:

[gateway] agent model: anthropic/claude-opus-4-7

The tester had no warning during setup that this model required credits. The team had to provide a special LiteLLM beta key to unblock the test.

Impact

High onboarding friction. For a beginner, this looks like an install failure even though the problem is model billing/default selection.

Suggested fix

  • Avoid defaulting first-run Windows QuickStart to a high-cost model without explicit confirmation.
  • Add billing/credit preflight during provider/model selection.
  • Prefer a cheap/default beta model for tester onboarding when available.
  • Make first-chat errors say: install succeeded, provider billing/auth failed.

Source

HeraldLabs beta QA report from Miriam Peter, 2026-05-30.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING