Multi-Label Intent Classification
Identifies single or multiple customer intents (e.g. "billing_support", "subscription_cancel") from free-form text.
Loading RsFlowHub...
High-accuracy customer intent classification and entity extraction API for support ticket routing and workflow automation.
https://www.rsflowhub.com/api/v1/ai/intent-detection
Customer Intent & Entity Recognition API is a production-ready cloud REST API endpoint hosted on RSFlowHub designed for developers building high-throughput web, mobile, and AI agent applications. It accepts structured JSON payloads via POST /api/v1/ai/intent-detection, executes sub-180ms inference across global edge regions, and returns deterministic, type-safe JSON envelopes without unpredictable hallucination.
X-API-Key Header
curl -X POST "https://www.rsflowhub.com/api/v1/ai/intent-detection" \
-H "Content-Type: application/json" \
-H "X-API-Key: rsh_live_your_api_key_here" \
-d '{"text":"I want to cancel my subscription on web and talk to the billing team.","intent_types":["billing_support","subscription_cancel"],"intent_entities":{"subscription_cancel":["channel"]}}'
<?php
$client = new \GuzzleHttp\Client();
$response = $client->post('https://www.rsflowhub.com/api/v1/ai/intent-detection', [
'headers' => [
'Content-Type' => 'application/json',
'X-API-Key' => 'rsh_live_your_api_key_here',
],
'json' => array (
'text' => 'I want to cancel my subscription on web and talk to the billing team.',
'intent_types' =>
array (
0 => 'billing_support',
1 => 'subscription_cancel',
),
'intent_entities' =>
array (
'subscription_cancel' =>
array (
0 => 'channel',
),
),
),
]);
echo $response->getBody();
const response = await fetch('https://www.rsflowhub.com/api/v1/ai/intent-detection', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'X-API-Key': 'rsh_live_your_api_key_here'
},
body: JSON.stringify({"text":"I want to cancel my subscription on web and talk to the billing team.","intent_types":["billing_support","subscription_cancel"],"intent_entities":{"subscription_cancel":["channel"]}})
});
const data = await response.json();
console.log(data);
import requests
url = "https://www.rsflowhub.com/api/v1/ai/intent-detection"
headers = {
"Content-Type": "application/json",
"X-API-Key": "rsh_live_your_api_key_here"
}
payload = {"text":"I want to cancel my subscription on web and talk to the billing team.","intent_types":["billing_support","subscription_cancel"],"intent_entities":{"subscription_cancel":["channel"]}}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
Identifies single or multiple customer intents (e.g. "billing_support", "subscription_cancel") from free-form text.
Extracts target entities such as order IDs, account emails, channel types, and requested action dates.
Returns numeric confidence scores (0.0 to 1.0) for each detected intent to trigger automated fallback rules.
Built for instant integration with Zendesk, Freshdesk, Intercom, and custom CRM ticket workflows.
See how developers integrate this API endpoint into production apps.
Classify incoming customer support emails to instantly route them to Billing, Technical Support, or Sales.
Understand customer request intent to trigger instant order tracking or return authorization workflows.
Flag cancellation and complaint intents immediately to trigger retention team alerts.
Comparing RSFlowHub's specialized API gateway vs raw multi-turn LLM prompts vs legacy regex rules.
| Evaluation Metric | RSFlowHub API | Raw LLM Prompts | Legacy Regex / Rules |
|---|---|---|---|
| Response Structure | Strict typed JSON envelope | Unstructured markdown or chat format | Brittle custom regex tuples |
| Latency Performance | 120ms - 220ms edge cached | 1,500ms - 4,000ms streaming | 50ms (Zero semantic capability) |
| Pricing Model | Flat 1 credit/request | Volatile token-based billing | High server maintenance overhead |
| Multi-Turn Hallucination | Zero (Deterministic validators) | Frequent schema drift & hallucinations | No semantic AI intelligence |
| Developer Integration | 3 lines cURL, PHP, JS, Python | Complex prompt engineering & retry loop | Fragile manual rule maintenance |
text
string
User message, email body, or chat prompt to analyze for intent.
intent_types
array
Optional list of allowed intent category labels to match against.
intent_entities
object
Optional custom entity schema mapping for targeted extraction.
All API endpoints return uniform JSON envelopes with status code, execution metadata, and data payload.
{
"status": "success",
"code": 200,
"message": "Processed successfully",
"data": {
"result": "Sample output result"
},
"meta": {
"credits_deducted": 1,
"execution_time_ms": 142
}
}
Everything you need to know about integrating and using Customer Intent & Entity Recognition API.
Get started in minutes with free welcome credits and instant API key generation.
⚡ 24h Bug Fix SLA: If you face any issues, submit them & we fix them within 24 hours.
💡 Custom APIs: Need custom AI models or APIs? Tell us and we will build them for you.