API reference · Live events

Get latency

GET/v1/latency

Per-source measured lead over the public webcast, median and 90th percentile, over the last 24 hours.

On this page

Auth. None. Without a token the call is served as Free (the Free delay and request budget, shared per IP); send Authorization: Bearer lb_… for your plan's.

Limits. Counts against your plan's API requests (60, 600 or 3,000 a minute on Free, Builder and Standard).

Request

Terminal

curl "https://api.langbot.ai/v1/latency"

Python

from langbot import LangbotClient

async with LangbotClient() as lb:
    for s in await lb.latency():
        print(s["source_id"], s["p50_lag_ms"], s["samples"])

TypeScript

import { LangbotClient } from "@langbotai/sdk";

const lb = new LangbotClient();
const sources = await lb.latency();
console.log(sources);

Response

200 OK

JSON

{
  "ts": 1793685348576,
  "window_ms": 86400000,
  "p50_lag_ms": 16200,
  "sources": [
    { "source_id": "src_nvda_q3_2026_dialin", "kind": "sip", "p50_lag_ms": 18740, "p90_lag_ms": 23100, "samples": 412, "last_ts": 1760051000000, "events_24h": 1210, "event_p50_lag_ms": 18100 }
  ],
  "spoken_to_emitted_ms": { "p50": 72, "p90": 114, "n": 7092, "window": "24h" }
}

Positive lag means ahead of the public webcast; null when it could not be measured. How it is measured: Live events.

Errors

Status	`code`	When
401	`token_invalid`	A token was sent and not recognised. Send a valid one, or none to call anonymously.
429	`rate_limited`	Over your request budget; wait `Retry-After` seconds.

Every error body is {"detail": …, "code": "…"}; branch on code. All codes: Errors.