# Get the live model

Source: https://langbot.ai/docs/api/live-events/get-live-model

`GET /v1/models/live`

During an event, the verified count so far per count market and the probability the count reaches what the market needs.

**Auth.** An API token: `Authorization: Bearer lb_…` ([create one](https://langbot.ai/app/tokens)). Signed-in web sessions work too.

**Limits.** One model call per call (100 a day on Free; unlimited on Builder and Standard). Served at your plan's delay (+60 s Free, +10 s Builder, +2 s Standard).

## Parameters

### Query parameters

| Name | Type | Required | Description |
|---|---|---|---|
| `event_id` | string | yes | A live event (`ev_…`). |
| `window_days` | integer | no | History window for the prior, in days. 1 to 3650. |

## Request

**curl**

```bash
curl "https://api.langbot.ai/v1/models/live?event_id=ev_nvda_q3_2026" \
  -H "Authorization: Bearer $LANGBOT_API_TOKEN"
```

**Python**

```python
from langbot import LangbotClient

async with LangbotClient() as lb:  # reads LANGBOT_API_TOKEN
    live = await lb.live_model("ev_nvda_q3_2026")
    for m in live["markets"]:
        print(m["ticker"], m["count"], m["needed"], m["model_p"])
```

**TypeScript**

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

const lb = new LangbotClient(); // reads LANGBOT_API_TOKEN
const live = await lb.liveModel("ev_nvda_q3_2026");
console.log(live.markets);
```

## Response

`200 OK`

```json
{
  "ts": 1760052000000,
  "delay_ms": 10000,
  "event": { "id": "ev_nvda_q3_2026", "status": "live" },
  "model": { "name": "live_threshold" },
  "elapsed_from": "speaker_on_air",
  "elapsed_minutes": 21.5,
  "count": 1,
  "markets": [
    { "ticker": "KXEARNINGSMENTIONNVDA-26OCT-AI10", "count": 6, "needed": 10, "mentions_still_needed": 4, "reached": false, "remaining_minutes": 38.5, "posterior_rate_per_minute": 0.29, "model_p": 0.88, "market_mid": 0.81, "difference": 0.07, "caveats": [] }
  ],
  "caveats": []
}
```

Recomputed on every request from the verified hits so far. `model_p` = P(count reaches `needed`) under a Poisson model of the remaining minutes. Not a signal.

## Errors

| Status | `code` | When |
|---|---|---|
| 401 | `auth_required` | No token was sent. |
| 401 | `token_invalid` | The token was not recognised (mistyped, revoked or expired). |
| 422 | `validation_error` | A parameter failed validation; `detail[].loc` names it. |
| 429 | `quota_exceeded` | Today's model calls are spent; `quota.resets_at` says when they reset. |
| 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).