What this error means

Unable to connect to API (ConnectionRefused) for 10 times (takes 3m) and then fails with an error is a Claude Code failure pattern reported for developers trying to fix persistent connectionrefused error when using claude code cli on linux after uninstall/reinstall — works on other machines. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #61320 on anthropics/claude-code opened May 21/22, 2026 by PonyLucky. After reinstalling Claude Code v2.1.147 on Linux (previously uninstalled 2 months ago), all model calls fail with ConnectionRefused for 10 retries (3 minutes) before final error. User deleted all config files (~/.claude.json, ~/.claude/, etc.) but problem persists. Works on another laptop with same account. No keyring or bun installed. api:anthropic + area:networking + platform:linux labels, 2 comments. Blocks paid subscription usage entirely. Distinct from duplicate reports (#56711, #56242, #60041) per author assertion.

Common causes

  • GitHub issue #61320 on anthropics/claude-code opened May 21/22, 2026 by PonyLucky. After reinstalling Claude Code v2.1.147 on Linux (previously uninstalled 2 months ago), all model calls fail with ConnectionRefused for 10 retries (3 minutes) before final error. User deleted all config files (~/.claude.json, ~/.claude/, etc.) but problem persists. Works on another laptop with same account. No keyring or bun installed. api:anthropic + area:networking + platform:linux labels, 2 comments. Blocks paid subscription usage entirely. Distinct from duplicate reports (#56711, #56242, #60041) per author assertion.

Quick fixes

  1. Confirm the exact error signature matches Unable to connect to API (ConnectionRefused) for 10 times (takes 3m) and then fails with an error.
  2. Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

  • Verify the command, editor, extension, or API client that produced the error.
  • Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
  • Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

  • Keep provider/tool configuration documented.
  • Record non-secret diagnostics such as tool version, provider name, model name, and command path.
  • Add a lightweight check before CI or production workflows depend on the tool.