Most text analysis solutions fall into one of two problems:
- Too expensive — OpenAI API costs money for every call
- Too complex — Hosting your own Hugging Face model requires infra, GPU, maintenance
I built TextAI Pro — a lightweight REST API that does the job without the overhead.
What it does
Two endpoints:
POST /analyze
- Sentiment: positive / negative / neutral
- Confidence score (0–1)
- Top keywords
- Word count
POST /summarize
- Auto-summary of any text
- Returns original length vs summary length
Quick start
Python
import requests
url = "https://textai-pro.p.rapidapi.com/analyze"
headers = {
"X-RapidAPI-Key": "YOUR_KEY",
"Content-Type": "application/json"
}
payload = {"text": "This product is absolutely amazing, I love it!"}
r = requests.post(url, json=payload, headers=headers)
print(r.json())
Response:
{
"sentiment": "positive",
"confidence": 0.92,
"keywords": ["product", "amazing", "love"],
"word_count": 8
}
JavaScript
const response = await fetch("https://textai-pro.p.rapidapi.com/analyze", {
method: "POST",
headers: {
"X-RapidAPI-Key": "YOUR_KEY",
"Content-Type": "application/json"
},
body: JSON.stringify({ text: "Great customer service, highly recommend!" })
});
const data = await response.json();
console.log(data);
Use cases
- Review monitoring — analyze customer feedback automatically
- Content moderation — flag negative or toxic content
- CRM enrichment — tag support tickets by sentiment before routing
- Chatbot routing — detect frustrated users and escalate
- News monitoring — track sentiment around keywords or brands
Pricing
| Plan | Price | Rate limit |
|---|---|---|
| BASIC | Free | 50 req/hr |
| PRO | $9.99/mo | 1,000 req/hr |
| ULTRA | $29.99/mo | 10,000 req/hr |
Try it
Free tier, no credit card required. Sign up to RapidAPI (free) and subscribe to BASIC to start.
Built this for a side project where I needed bulk sentiment analysis on customer reviews. OpenAI was too expensive for 50k+ records per day. This runs on dedicated infra and costs a fraction.
Feedback welcome — especially on what other endpoints would be useful.
Top comments (0)