---
title: "List In Flight"
method: GET
path: "/v1/usage/in-flight"
tags: ["usage"]
---

# List In Flight

`GET /v1/usage/in-flight`

Requests the gateway is currently serving, longest-running first.

A usage row is written when a request settles, so the log alone cannot answer
"is anything happening right now": on a slow backend, a 30-second local model
call is invisible until it finishes. This reports what is in progress.

Read from an in-memory registry, so it describes the process that answers this
call and not the deployment: behind a load balancer, consecutive polls reach
different otari processes, and there is no deployment-wide total to ask for.
``total`` is the true in-flight count for the answering process even when
``requests`` is capped.

## Response `200`

Successful Response

- InFlightResponse — The requests in flight on the answering worker.
  - `requests` InFlightEntry[], required
    - `api_key_id` string, nullable, required
    - `elapsed_ms` integer, required
    - `endpoint` string, required
    - `id` string, required
    - `model` string, required
    - `policy_name` string, nullable, required
    - `provider` string, nullable, required
    - `started_at` string, date-time, required
    - `user_id` string, nullable, required
  - `total` integer, required

---

[API](https://skmtc.net/mozilla-ai/apis/otari.md) · [All operations](https://skmtc.net/mozilla-ai/apis/otari/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/mozilla-ai/otari/revisions/866dfb3fb7eb/schema)