---
title: "Liveness check"
method: GET
path: "/tt-liveness"
tags: ["Health"]
---

# Liveness check

`GET /tt-liveness`

Liveness probe (same as Python tt-liveness). Returns 200 with {"status": "alive", ...system status} when the process can respond. model_ready in the body reflects whether any worker has warmed up. Does not return 503 for model not ready; 500 only on unrecoverable failure.

## Response `200`

Process is alive; body includes status alive and system status (model_ready, workers, queue)

- ReadyResponse
  - `model_ready` boolean — Whether the model is ready for inference
  - `queue_size` integer — Current number of requests in queue
  - `max_queue_size` integer — Maximum queue capacity
  - `device` string — Device type
  - `worker_info` object — Worker status keyed by worker ID (Python-server-compatible format)
  - `runner_in_use` string — Active runner identifier (image services only). Mirrors the Python ModelRunners enum (e.g. 'tt-sdxl-trace', 'tt-sdxl-image-to-image', 'tt-sdxl-edit'). Omitted when the active service does not expose a runner.

## Other responses

- `500` — Unrecoverable failure (e.g. no service configured, exception)

---

[API](https://skmtc.net/tenstorrent/apis/tt-media-server-api-c-drogon.md) · [All operations](https://skmtc.net/tenstorrent/apis/tt-media-server-api-c-drogon/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/tenstorrent/tt-media-server-api-c-drogon/revisions/f1176db3fd15/schema)