Usage Summary

Definition

What is the Usage Summary?

Usage Summary is a REST API on RSFlowHub for web, mobile and AI agent applications. Send a JSON request to GET /api/v1/account/usage-summary with your API key; RSFlowHub runs it on a tuned AI model, falls back to a backup provider if needed, and returns a structured JSON result, usually within 1 to 3 seconds.

Category: Account & Usage
Endpoint: GET /api/v1/account/usage-summary
Authentication: X-API-Key header
Price: Free per call
Rate limit: 10 to 120 requests / minute by plan
Typical response: 1 to 3 seconds
Format: JSON, UTF-8

Request parameters

Send these fields as a JSON body. An invalid or missing field returns a 422 error that names the field.

No request body needed

Send the request with your X-API-Key header only.

Code examples

Copy, replace rfh_your_api_key with your key and run. Prefer a client library? See the official SDKs.

request.sh

curl -X POST "https://rsflowhub.com/api/v1/account/usage-summary" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: rfh_your_api_key" \
  -d '[]'

client.php

<?php

$client = new \GuzzleHttp\Client();
$response = $client->post('https://rsflowhub.com/api/v1/account/usage-summary', [
    'headers' => [
        'Content-Type' => 'application/json',
        'X-API-Key'    => 'rfh_your_api_key',
    ],
    'json' => array (
    ),
]);

echo $response->getBody();

client.js

const response = await fetch('https://rsflowhub.com/api/v1/account/usage-summary', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': 'rfh_your_api_key'
  },
  body: JSON.stringify([])
});

const data = await response.json();
console.log(data);

main.py

import requests

url = "https://rsflowhub.com/api/v1/account/usage-summary"
headers = {
    "Content-Type": "application/json",
    "X-API-Key": "rfh_your_api_key"
}
payload = []

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Response

Every RSFlowHub endpoint uses the same envelope, so one parser handles all of them. Failed calls are not charged.

response.json

{
    "success": true,
    "request_id": "req_3f9a2c7e-5b1d-4e8a-9c2f-7d6e1a0b4c8d",
    "data": {
        "result": {
            "message": "See the API reference for the full result schema."
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

error.json

{
    "success": false,
    "request_id": "req_8c1d4e2a-7f3b-4a9c",
    "error": {
        "code": "VALIDATION_ERROR",
        "message": "The given data was invalid.",
        "details": {
            "text": [
                "This field is required."
            ]
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

Envelope fields
Field	Type	Meaning
`success`	boolean	true when the call worked, false on any error.
`request_id`	string	Unique id for this call. Quote it when you contact support.
`data.result`	object	The result of this endpoint (see the example).
`error`	object	Only on failure: code, message and details per field.
`meta`	object	API version and server timestamp.

All error codes: Errors reference

Features

Ultra-Low Latency Inference

Each endpoint is tuned for one task and usually returns its result in 1 to 3 seconds.

Enterprise SLA & Rate Limiting

A circuit breaker watches every AI provider and retries failed calls on a backup model.

Strict JSON Envelope Output

Results are validated and returned as structured fields, so you parse JSON instead of cleaning up free text.

Multilingual by Default

The underlying models understand and answer in all major languages, so one endpoint serves global users.

Use cases

How teams use the Usage Summary in production.

SaaS Platforms

Automated Product Workflows

Embed Usage Summary directly into user onboarding and background data processing pipelines.

Input: Incoming asynchronous customer event payload
Output: Clean structured AI output ready for DB storage

85% Reduction in manual operations

Customer Operations

High-Volume Triage & Routing

Process inbound tickets and requests with Usage Summary for instant categorization.

Input: Unstructured user inquiry text
Output: Normalized intent, entity tags & routing priority

3x Faster time-to-resolution

Enterprise Systems

Mission-Critical Compliance

Validate and enrich enterprise communication records with Usage Summary.

Input: Batch customer interactions or messages
Output: Standardized audited records with safety checks

100% Policy adherence verified

Usage Summary vs building it yourself

The same job done three ways.

Topic	RSFlowHub API	Raw LLM prompts	Rules / regex
Output	Validated JSON fields	Free text you have to parse	Fixed patterns only
Setup	One POST request, no prompts	Write and maintain prompts and parsing	Write and maintain rule lists
Provider outage	Automatic fallback to a backup model	You build retries and a second vendor	Not applicable
Pricing	Free per call, failed calls free	Per token, per vendor	Your own servers and upkeep
Understands context	Yes, AI model	Yes, AI model	No, keywords only

Frequently asked questions

What is Usage Summary and how does it work?

Usage Summary is a production-grade developer AI API hosted on RSFlowHub providing deterministic, low-latency processing via standard REST JSON requests.

How do I authenticate requests to the Usage Summary endpoint?

Pass your secret API key in the 'X-API-Key' HTTP header. You can generate and rotate production keys anytime in your RSFlowHub developer dashboard.

What is the expected latency for Usage Summary?

Most requests complete in 1 to 3 seconds, depending on input length and the AI model. Identical repeat requests are served from cache and return faster.

How are credits billed for Usage Summary calls?

Calls consume 0 base credit per successful request. Failed requests due to validation or server errors do not deduct credits.

Can I use Usage Summary with Python, Node.js, or PHP?

Yes! Usage Summary is a universal REST API compatible with any HTTP client including cURL, Axios, Guzzle, Requests, and native fetch.

More Account & Usage APIs

View category

Text & Language

Intent Detection

Detect user intent from natural language messages for routing, support, and workflow automation.

1 credit
Text & Language

Translation

Translate text between multiple languages using AI for high-quality contextual translations.

1 credit
Conversational AI

Chat Completion

Standard conversational AI endpoint for interactive chat and assistant-like applications.

1 credit

What is the Usage Summary?

Request parameters

No request body needed

Code examples

Response

Features

Ultra-Low Latency Inference

Enterprise SLA & Rate Limiting

Strict JSON Envelope Output

Multilingual by Default

Use cases

Automated Product Workflows

High-Volume Triage & Routing

Mission-Critical Compliance

Usage Summary vs building it yourself

Frequently asked questions

Start using the Usage Summary

Sign in to continue

Usage Summary

What is the Usage Summary?

No request body needed

Ultra-Low Latency Inference

Enterprise SLA & Rate Limiting

Strict JSON Envelope Output

Multilingual by Default

Automated Product Workflows

High-Volume Triage & Routing

Mission-Critical Compliance

Intent Detection

Translation

Chat Completion

Start using the Usage Summary