{"version":"2.1.295","anchor":"gateway-docs-501-not-supported-should-send-x-should-retry","canonical_anchor":"gateway-docs-501-not-supported-should-send-x-should-retry","heading":"Gateway guide: send x-should-retry: false with a 501 not supported response","tier":"use","area":"LLM Gateway","scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295\/e\/gateway-docs-501-not-supported-should-send-x-should-retry","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295","markdown":"### Gateway guide: send `x-should-retry: false` with a 501 not supported response\n\nThe bundled gateway guide now says a 501 not supported response should send `x-should-retry: false`, or Claude Code retries once first\n\n**What**\n\nAn LLM gateway is a server you put between Claude Code and the model provider. Claude Code's bundled guidance for gateways now says that when a gateway replies with a 501 `not_supported` error, it should also send the header `x-should-retry: false`. Without that header, Claude Code tries the request once more, about half a second later, before it falls back.\n\n**Why**\n\nIf you run a gateway, sending this header saves a pointless retry and a short delay whenever an endpoint is not available.\n\n- Area: LLM Gateway\n- Names: `x-should-retry`\n- Tier: Use it now\n- Useful: 2\/5\n- Signal: 1\/5\n- Scope: org\n- Heads-up: no"}