{"version":"2.1.285","anchor":"third-party-model-access-check-results-are-remembered-across","canonical_anchor":"third-party-model-access-check-results-are-remembered-across","heading":"Claude Code remembers which models your AWS or Google Cloud account can use","tier":"notice","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285\/e\/third-party-model-access-check-results-are-remembered-across","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285","markdown":"### Claude Code remembers which models your AWS or Google Cloud account can use\n\nModel access checks for AWS and Google Cloud accounts are now saved and reused at start-up, unless CLAUDE_CODE_SKIP_MODEL_ACCESS_MEMORY is set\n\n**Unclear.** It is not clear how long saved results are kept or exactly which providers are covered.\n\n**What**\n\nWhen you use Claude through AWS or Google Cloud credentials, Claude Code checks at start-up which models your account can use. It now saves each result, allowed or refused, per account in a `cache\/model-access.json` file and can reuse it on later starts.\n\nTo tell accounts apart, Claude Code builds a fingerprint of your AWS config and credentials files or your gcloud identity files. If one of those files is over 4 MB or is not a regular file, saved results are not reused.\n\nTo turn this memory off, set `CLAUDE_CODE_SKIP_MODEL_ACCESS_MEMORY`. Related log lines start with `[3p-model-memory]`.\n\n**Why**\n\nStart-up can skip some model checks, so it may be quicker. A saved answer can go out of date, though: if your model access changes and Claude Code still behaves as before, set `CLAUDE_CODE_SKIP_MODEL_ACCESS_MEMORY`.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5"}