Health API

GET /api/v1/health — live snapshot with status, checked_at, and per-component health.

Get a public snapshot of AnyRouter's health: overall status, checked_at and a components breakdown. No API key needed.

This endpoint is unauthenticated. A default curl User-Agent may get 403 HTML from bot protection on the apex. Use https://api.anyrouter.dev/api/v1/health, or send a User-Agent such as -A "my-status-probe/1.0".

Request

No parameters, no auth header. Poll at ≥ 60 s (see Caching).

GET /api/v1/health HTTP/1.1

If a client gets HTML instead of JSON, use the API host (same Worker as https://anyrouter.dev/api/v1/health):

curl https://api.anyrouter.dev/api/v1/health

Response

Success is always HTTP 200. Read status in the body, not the HTTP code. Each component has its own status:

components.api is last-hour generation error rate (can be down during a traffic spike). BYOK requests (generations.is_byok = 1) are excluded. A failed request counts as an error only when its final attempt was a real platform outage (404/410, any 5xx, or failure_class health/capability); key-permission failures (401/403, credential) never count.
components.providers lists routing backend ids that served traffic in the last hour (cloudflare), not catalog owners (openai, z-ai) and not -byok/-pool backends. Idle backends are omitted. Generations whose provider_id is not a public backend appear as unattributed, so this list and components.api.data.requests_1h share one window. Quarantine, budget-exhausted and smoke-exclusion override the traffic status, so a skipped backend never reads healthy. Errors count by the same real-outage rule as components.api.
components.routing.summary.healthy is how many upstreams are routable; it subtracts quarantined and budget-exhausted backends.
components.smoke_tests.last_run is the daily catalog smoke (00
UTC); data.stale is true only when last_run is older than two days.
events lists upstream status-change events, newest first, capped at 50. -byok/-pool upstreams never appear.

{
  "status": "healthy",
  "description": "All systems operational.",
  "version": "1.4.0",
  "checked_at": "2026-08-18T12:00:00.000Z",
  "components": {
    "api": {
      "status": "healthy",
      "description": "Processing requests normally. 12847 requests in the last hour with 2.1% error rate.",
      "note": "Derived from the last 1 hour of traffic.",
      "data": {
        "requests_1h": 12847,
        "error_rate": 0.021,
        "latency_ms": { "avg": 340 },
        "cache_hit_rate": 0.35
      }
    },
    "providers": {
      "status": "healthy",
      "description": "All 1 providers that served traffic are operational.",
      "note": "Each row is a routing backend id (`generations.provider_id`), not a catalog model owner. Status is the last-hour error rate, overlaid with quarantine / budget-exhausted / smoke-exclusion.",
      "data": {
        "providers": [
          {
            "name": "cloudflare",
            "status": "healthy",
            "description": "Operating normally (5421 requests, 1.2% errors).",
            "latency_ms": 120,
            "requests_1h": 5421,
            "error_rate": 0.012
          }
        ]
      }
    },
    "smoke_tests": {
      "status": "healthy",
      "description": "All 80 tested models passed.",
      "note": "The daily smoke-test workflow (00:00 UTC) sends a real one-token request through chat/completions, responses, and messages.",
      "data": {
        "total": 80,
        "passed": 80,
        "failed": 0,
        "skipped": 0,
        "last_run": "2026-08-18T00:00:00.000Z",
        "stale": false,
        "cadence": "0 0 * * *"
      }
    },
    "workflows": {
      "status": "healthy",
      "description": "All 8 scheduled workflows are running on cadence.",
      "note": "Each scheduled workflow that has recorded a run is checked against its last run. Jobs that have never run are omitted.",
      "data": {
        "healthy": 8,
        "stale": 0,
        "failing": 0,
        "never_ran": 0,
        "workflows": [
          {
            "kind": "gateway-log-sync",
            "label": "Gateway log sync",
            "state": "healthy",
            "last_status": "success",
            "last_run_at": "2026-08-18T11:45:00.000Z",
            "age_hours": 0.1,
            "detail": "Last run success 0.1h ago."
          }
        ]
      }
    },
    "routing": {
      "status": "healthy",
      "description": "All 84 routing upstreams are healthy.",
      "note": "Live routing health from the smoke-cooldown store, plus active quarantine and monthly-budget suppression.",
      "data": {
        "summary": {
          "total": 84,
          "healthy": 84,
          "deprioritized": 0,
          "excluded": 0,
          "quarantined": 0,
          "budget_exhausted": 0
        },
        "degraded": [],
        "probes": { "checked_at": "2026-08-18T11:08:00.000Z", "stale": false }
      }
    }
  },
  "events": [
    {
      "at": "2026-08-18T11:10:00.000Z",
      "upstream_id": "cerebras",
      "name": "Cerebras",
      "from": "healthy",
      "to": "degraded",
      "message": "HTTP 503: Service Unavailable"
    }
  ]
}

Field	Type	Description
`status`	`"healthy" \| "degraded" \| "partial" \| "down" \| "no_signal"`	Overall state. Same enum is used on every component. `partial` means some components are degraded while routing still works. `no_signal` means there is not enough recent traffic to assess.
`description`	string	Human-readable summary of the overall state.
`version`	string	Release tag of the currently-deployed Worker.
`checked_at`	string	ISO 8601 timestamp of this snapshot.
`components`	object	Breakdown for `api`, `providers`, `smoke_tests`, `workflows`, and `routing`. `smoke_tests`, `workflows`, and `routing` may be `null`.
`events`	array	Chronological upstream status-change events, newest first (capped at 50).

Every component object has status (same enum), description, note (how the check is derived), and data.

Nested field	Type	Description
`components.api.data.requests_1h`	integer	Requests in the last hour.
`components.api.data.error_rate`	number	Fraction of those requests that errored (0–1).
`components.api.data.latency_ms.avg`	number	Average latency in milliseconds.
`components.api.data.cache_hit_rate`	number	Fraction of requests that hit the prompt cache (0–1).
`components.providers.data.providers[]`	array	Per-backend rows (`name` is a routing backend id such as `cloudflare`, not a catalog owner). Includes `status`, `description`, optional `latency_ms` / `error_rate`, and `requests_1h`. Only backends with last-hour traffic appear. Not a top-level `providers` array.
`components.smoke_tests.data`	object	`total`, `passed`, `failed`, `skipped`, `last_run` (ISO 8601 or `null`), `stale` (true only after 2× the daily cadence), and `cadence` (`0 0 * * *`).
`components.workflows.data`	object	Counts `healthy`, `stale`, `failing`, `never_ran`, plus `workflows[]` (`kind`, `label`, `state`, `last_status`, `last_run_at`, `age_hours`, `detail`). Jobs that never ran or are intentionally paused are omitted, so `never_ran` is always `0`.
`components.routing.data.summary`	object	`total`, `healthy`, `deprioritized`, `excluded`, `quarantined`, `budget_exhausted`, over public platform upstreams only (unnamed and `-byok`/`-pool` upstreams are never counted). `healthy` subtracts quarantined / budget-exhausted backends that still look smoke-healthy.
`components.routing.data.degraded[]`	array	Degraded upstreams with `id` (routing backend id, e.g. `google-agent-platform`), `name` (display label — not unique), `logo`, and `state` (`deprioritized`, `excluded`, `quarantined`, or `budget_exhausted`). A backend degraded in several ways appears once per state.
`components.routing.data.probes`	object	`checked_at` (ISO time of the newest upstream reachability check, or `null`) and `stale`. `stale` is `true` when no check has run for over 2 hours; `routing` then reports `degraded`, because its states may be out of date.
`events[]`	array	Each entry has `at` (ISO 8601), `upstream_id`, its display `name`, `from`/`to` (`healthy`, `degraded`, `down`, or `unknown`), and an optional `message` from the probe.

Treat any top-level status other than healthy as not fully operational. Pair provider rows with /api/v1/providers for logos and descriptions.

Responses also include X-RateLimit-Limit, X-RateLimit-Window, and X-RateLimit-Tier (anonymous callers use the IP tier). A 429 honors Retry-After. See Rate Limits.

Examples

curl https://api.anyrouter.dev/api/v1/health

import httpx

health = httpx.get("https://api.anyrouter.dev/api/v1/health").json()
if health["status"] != "healthy":
    print(health["description"], health["components"]["providers"]["status"])

const res = await fetch("https://api.anyrouter.dev/api/v1/health")
const health = await res.json()
if (health.status !== "healthy") {
  console.warn(health.description, health.components)
}

Status codes

HTTP	Body `status`	Meaning
200	`healthy`	All scored components are healthy.
200	`partial` / `degraded` / `no_signal` / `down`	One or more components are unhealthy or lack traffic. Inference may still succeed via fallback.
429	—	Anonymous IP cap (300 req / 60s). Honor `Retry-After`.

This endpoint does not use HTTP 503 for a down component — read status and components.*.status.

Caching

Anonymous responses are cacheable. The Worker stamps:

Cache-Control: public, max-age=60, s-maxage=300, stale-while-revalidate=600

Browsers reuse the body for 60 s; the edge keeps it 5 minutes and may serve it stale for up to 10 minutes while refreshing. Poll at ≥ 60 s.

AnyRouter routes requests to third-party models. Models and outputs are provided as is, with no warranty; you use them at your own risk. Disclaimer