# Get stats

Source: https://langbot.ai/docs/api/public/get-stats

`GET /v1/stats`

Public counters for the live record, including the measured time from a word being spoken to the feed sending it.

**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

**curl**

```bash
curl "https://api.langbot.ai/v1/stats"
```

**Python**

```python
from langbot import LangbotClient

async with LangbotClient() as lb:
    stats = await lb.stats()
    print(stats["spoken_to_emitted_ms"])
```

**TypeScript**

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

const lb = new LangbotClient();
const stats = await lb.stats();
console.log(stats.spoken_to_emitted_ms);
```

## Response

`200 OK`

```json
{
  "ts": 1793685901548,
  "sources_this_week": 61,
  "events_today": 73818,
  "phrases_today": 1491,
  "p50_lag_ms": null,
  "spoken_to_emitted_ms": {"p50": 72, "p90": 113, "n": 7118, "window": "24h"},
  "events_live": 0,
  "markets_open": 33368,
  "clients_connected": 0
}
```

A real response from the API; long lists are cut to their first items.

`spoken_to_emitted_ms` is measured over real sources in the last 24 hours (`n` samples); demo and test traffic is left out of every figure.

## 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](https://langbot.ai/docs/api#errors).