{
  "slug": "vercel-ai-gateway-api-keys-create-adds-api-key-creation-3ed99cbece78",
  "title": "vercel ai-gateway api-keys create adds API-key creation",
  "tools": [
    "vercel"
  ],
  "tags": [
    "agent"
  ],
  "introduced_at": "2026-04-14T07:15:49.000Z",
  "announced_at": "2026-04-14T07:15:49.000Z",
  "effective_at": null,
  "date_basis": "source-publication",
  "status": "unknown",
  "how": {
    "incantation": "When creating an AI Gateway API key, run `vercel ai-gateway api-keys create`; add `--budget` and optionally `--refresh-period` to set an optional quota. Save the returned key immediately, because it cannot be retrieved again.",
    "examples": [
      "vercel ai-gateway api-keys create",
      "vercel ai-gateway api-keys create --name <NAME> --budget <DOLLARS> --refresh-period <PERIOD>"
    ],
    "gotchas": [
      "Version: 51.2.1",
      "--name <NAME>: Human-readable API key name.",
      "--budget <AMOUNT>: Quota budget in dollars; minimum 1.",
      "--refresh-period <PERIOD>: Quota refresh cadence: `daily`, `weekly`, `monthly`, or `none`; default is `none`.",
      "Prerequisite: Install Vercel CLI and authenticate before performing administrative tasks. The key is created under the current CLI scope.",
      "Quota limits are optional."
    ]
  },
  "why_it_matters": "Create an AI Gateway API key for a coding project, optionally with quota limits.",
  "sources": [
    "https://github.com/vercel/vercel/releases/tag/vercel%4051.2.1",
    "https://github.com/vercel/vercel/blob/vercel%4051.2.1/packages/cli/src/commands/ai-gateway/command.ts",
    "https://vercel.com/docs/ai-gateway/observability-and-spend/budgets",
    "https://vercel.com/docs/cli"
  ],
  "rank": 0.95026,
  "judge": {
    "publish": true,
    "judge_model": "codex-cli/gpt-6-luna+typesafe/jev-1.13.0",
    "prompt_version": "extract-v7+enrich-v2+judge-v2x3+jev-publish-v1"
  },
  "review_state": "approved",
  "provenance": {
    "run_id": "backfill-20261007",
    "verdict_id": "backfill-20261007:backfill-20261007-484db5afa44a87db-0:gate",
    "evidence_hash": "556be32c12b28a708ec9ef96397ec3c8c97eaa9b7852a2cc8957ab54d388b380"
  },
  "review": {
    "draft_hash": "9d8daf087f5c317fdd185e8ba053e6feda7356e06cb6f810c3a1607291cf1ca9",
    "reviewer": "publication-gate",
    "reviewed_at": "2026-10-07T00:00:00.000Z",
    "decision": "backfill-20261007:gate",
    "reason": "3 of 3 judge runs approved with p_yes >= 0.9 (mean 0.95 >= 0.9; 2 needed) and Jev gave 0.73 (>= 0.6 needed)."
  }
}
