{"version":"2.1.269","anchor":"gateway-model-discovery-request-timeout-is-now-configurable","canonical_anchor":"gateway-model-discovery-request-timeout-is-now-configurable","heading":"Gateway model-discovery request timeout is now configurable via env var","tier":"use","area":"Gateway","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/gateway-model-discovery-request-timeout-is-now-configurable","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Gateway model-discovery request timeout is now configurable via env var\n\nNew `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` env var configures the LLM gateway's model-discovery timeout\n\n**What**\n\nWhen Claude Code queries an LLM gateway's `\/v1\/models` endpoint to discover available models, it waits for a response before giving up. That wait time was previously fixed in code; it can now be set with the `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` environment variable, and still defaults to 3000ms (3 seconds) if unset. The failure log also now says explicitly when the request failed because of a timeout, rather than a generic failure.\n\n**Why**\n\nUsers running a slower or more distant LLM gateway can extend the timeout instead of hitting a discovery failure at the fixed default, and the clearer log message makes timeout-related discovery failures easier to diagnose.\n\n- Area: Gateway\n- Names: `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 2\/5"}