---
title: "GET /health"
method: GET
path: "/health"
tags: ["health"]
---

# GET /health

`GET /health`

## Response `200`

Gateway cluster health

- HealthResponse
  - `cluster` ClusterSummary, required
    - `gpu_count` integer, required
    - `models_loaded` integer, required
    - `total_qps` number, double, required
    - `worker_count` integer, required
  - `configured_gpu_types` string[], required
  - `live_gpu_types` string[], required
  - `models` ModelInfo[], required
    - `gpu_types` string[], required
    - `name` string, required
    - `state` string, required
    - `total_queue_depth` integer, required
    - `worker_count` integer, required
  - `pending_generation` PendingGenerationSnapshot
    - `groups` PendingGenerationGroup[], required
      - `active_streams` integer, required
      - `count` integer, required
      - `display_model` string, required
      - `model` string, required
      - `oldest_request_age_ms` integer, required
      - `pool` string, required
      - `republished` integer, required
      - `waiting_first_chunk` integer, required
    - `total` integer, required
  - `status` string, required
  - `type` string, required
  - `workers` WorkerInfo[], required
    - `bundle` string, required
    - `bundle_config_hash` string, required
    - `gpu` string, required
    - `gpu_count` integer, required
    - `healthy` boolean, required
    - `inflight_batches` integer, required
    - `loaded_models` string[], required
    - `memory_total_bytes` integer, required
    - `memory_used_bytes` integer, required
    - `name` string, required
    - `pending_cost` integer, required
    - `queue_depth` integer, required
    - `ready_gpu_slots` integer, required
    - `url` string, required

## Other responses

- `401` — Missing or invalid bearer token (inference token)
- `500` — Gateway auth enabled but no tokens configured

## Changes

> 41 revisions in range; 1 could not be searched.

- **2026-07-09** `e887405cf028` — 3 info
  - added the required property `workers/items/inflight_batches` to the response with the `200` status
  - added the required property `workers/items/pending_cost` to the response with the `200` status
  - added the required property `workers/items/ready_gpu_slots` to the response with the `200` status
- **2026-06-22** `f4d021dbd5f5` — 1 info
  - added the optional property `pending_generation` to the response with the `200` status
- **2026-05-08** `a499d5bea359` — 3 breaking, 1 warning
  - removed the required property `workers/items/inflight_batches` from the response with the `200` status
  - removed the required property `workers/items/pending_cost` from the response with the `200` status
  - removed the required property `workers/items/ready_gpu_slots` from the response with the `200` status
  - removed the optional property `pending_generation` from the response with the `200` status

[Change history](https://skmtc.dev/superlinked/apis/sie-gateway/changes/health/get.md)

---

[API](https://skmtc.dev/superlinked/apis/sie-gateway.md) · [All operations](https://skmtc.dev/superlinked/apis/sie-gateway/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/superlinked/sie-gateway/revisions/78eeecd83405/schema)