> ## Documentation Index
> Fetch the complete documentation index at: https://quantura.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Get started

> Authenticate, inspect access, and submit an asynchronous ensemble forecast.

# Get started

Create a personal API key in **Account → Developer → API Keys**. Copy the secret when it is created; Quantura does not return it again.

## Inspect effective access

```bash theme={null}
curl \
  -H "Authorization: Bearer $QUANTURA_API_KEY" \
  "https://quantura.studio/api/v1/me/access"
```

The response describes the token scopes, personal plan, accessible workspaces, and current role in each workspace.

## Submit a forecast

Forecast inference is asynchronous. A successful request returns HTTP `202` and a server-generated forecast identifier.

```bash theme={null}
curl -X POST \
  -H "Authorization: Bearer $QUANTURA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: pltr-balanced-30-sessions" \
  "https://quantura.studio/api/v1/ensemble-forecasts" \
  -d '{
    "source": {"type": "ticker", "symbol": "PLTR", "field": "close"},
    "prediction_length": 30,
    "horizon_mode": "trading_sessions",
    "quantiles": [0.01, 0.1, 0.25, 0.5, 0.75, 0.9, 0.99],
    "transform": "auto",
    "models": {
      "prophet": {"enabled": true, "weight": 0.5},
      "chronos": {"enabled": true, "weight": 0.5}
    }
  }'
```

Poll the returned `status_url` until the job is `completed` or `failed`. Use the download endpoint for CSV or JSON after completion.

<Warning>
  Model availability depends on the current workspace plan, runtime, and licensing. Query `GET /api/v1/forecast/models` before building a model selector.
</Warning>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.