# LUIS Runtime Client API

> LUIS Runtime Client API on Apizie: 4 endpoints (Gets the predictions for an application version., Gets the predictions for an application version., Gets the predictions for an application slot., Gets the predictions for an application slot.) returned as clean JSON through one API key. Send your own provider key in the x-upstream-key header. Call it over REST at https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/{endpoint} or from Claude, ChatGPT and Cursor through the Apizie MCP server. Free plan: 1,000 requests a month.

- Project key: `cloud:azure-cognitiveservices-luisruntime`
- Category: Cloud
- Status: byok
- Source: https://learn.microsoft.com/rest/api/azure/
- Page: https://apizie.tech/api/cloud/azure-cognitiveservices-luisruntime
- OpenAPI: https://apizie.tech/api/cloud/azure-cognitiveservices-luisruntime/openapi.json



## Endpoints

### Gets the predictions for an application version.
`GET https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-version-prediction-get` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com). |
| appId | string | yes | The application ID. |
| versionId | string | yes | The application version ID. |
| query | string | yes | The query to predict. |
| verbose | boolean | no | Indicates whether to get extra metadata for the entities predictions or not. |
| show-all-intents | boolean | no | Indicates whether to return all the intents in the response or just the top intent. |
| log | boolean | no | Indicates whether to log the endpoint query or not. |

### Gets the predictions for an application version.
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-version-prediction` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com). |
| appId | string | yes | The application ID. |
| versionId | string | yes | The application version ID. |
| verbose | boolean | no | Indicates whether to get extra metadata for the entities predictions or not. |
| show-all-intents | boolean | no | Indicates whether to return all the intents in the response or just the top intent. |
| log | boolean | no | Indicates whether to log the endpoint query or not. |
| body | object | yes | JSON request body |

### Gets the predictions for an application slot.
`GET https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-slot-prediction-get` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com). |
| appId | string | yes | The application ID. |
| slotName | string | yes | The application slot name. |
| query | string | yes | The query to predict. |
| verbose | boolean | no | Indicates whether to get extra metadata for the entities predictions or not. |
| show-all-intents | boolean | no | Indicates whether to return all the intents in the response or just the top intent. |
| log | boolean | no | Indicates whether to log the endpoint query or not. |

### Gets the predictions for an application slot.
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-slot-prediction` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com). |
| appId | string | yes | The application ID. |
| slotName | string | yes | The application slot name. |
| verbose | boolean | no | Indicates whether to get extra metadata for the entities predictions or not. |
| show-all-intents | boolean | no | Indicates whether to return all the intents in the response or just the top intent. |
| log | boolean | no | Indicates whether to log the endpoint query or not. |
| body | object | yes | JSON request body |

## Example
```
curl "https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-version-prediction-get" \
  -H "x-api-key: $APIZIE_KEY" \
  -H "x-upstream-key: $PROVIDER_KEY"
```

## FAQ

### How do I call the LUIS Runtime Client API?
Create a free Apizie key, then send GET https://apizie.tech/v1/cloud:azure-cognitiveservices-luisruntime/prediction-get-version-prediction-get with the header x-api-key. Every endpoint returns { project, data, timestamp }.

### Is the LUIS Runtime Client API free on Apizie?
Yes. The Free plan includes 1,000 requests a month at 100 requests a minute, no credit card. LUIS Runtime Client itself also needs your own key from azure.com.

### Can AI agents use the LUIS Runtime Client API?
Yes. Add the Apizie MCP server (https://apizie.tech/mcp) to Claude, ChatGPT, Cursor or VS Code, then ask in plain language. The agent calls run_scraper with project key cloud:azure-cognitiveservices-luisruntime.

### What is the status of the LUIS Runtime Client API?
Needs your own provider key (bring your own key)