v3 models now live — 40% faster inference

One API for
understanding language.

NLPort gives developers a single, fast endpoint for sentiment analysis, embeddings, summarization, entity extraction, and translation — in 95+ languages. No ML infrastructure required.

★★★★★ Trusted by 8,400+ developers · 1.2B requests/mo
cURL
Python
Node
# Analyze sentiment in one call curl https://nlport.ptlux.pro/v3/analyze \ -H "Authorization: Bearer nlp_live_••••" \ -H "Content-Type: application/json" \ -d '{ "text": "NLPort shipped this in a weekend. Incredible.", "tasks": ["sentiment", "entities"] }'
200 OK · 38ms · model nlp-v3
{ "sentiment": { "label": "positive", "score": 0.97 }, "entities": [{ "text": "NLPort", "type": "ORG" }] }

Powering language features at

◆ Quantyx Northwind ⬡ Heliograph Vela AI ◎ Pulsedeck Зефир

Everything you need to
process natural language

One consistent API surface across every task. Mix and match in a single request — pay only for what you use.

Sentiment & Emotion

Detect polarity, intensity and fine-grained emotions across reviews, tickets and social posts in real time.

POST /v3/analyze

Embeddings

1536-dim vectors for semantic search, clustering and RAG pipelines. Batch up to 2,048 inputs per call.

POST /v3/embed

Summarization

Abstractive and extractive summaries with controllable length. Handles documents up to 128k tokens.

POST /v3/summarize

Entity Extraction

Named entities, custom schemas and relationship mapping. Pull structured JSON from messy unstructured text.

POST /v3/extract

Translation

Neural translation across 95+ languages with terminology control and document-level context preservation.

POST /v3/translate

Classification

Zero-shot and few-shot text classification. Define your own labels — no training data or fine-tuning required.

POST /v3/classify

Try it right here

Type some text, pick a task, and see exactly what the API returns. No sign-up needed.

Interactive Demo

live endpoint · sandbox
Sentiment
Entities
Summary
Language
// Output will appear here…
0
Median p50 latency
0
Languages supported
99.98%
API uptime (90d)
0
Requests per month

Pay per request. Scale freely.

Start free with 10,000 calls/month. Upgrade only when you grow.

Free
$0/mo

For prototypes and side projects. No card required.

  • 10,000 requests / mo
  • All NLP tasks
  • v3 models
  • Community support
  • Batch endpoints
  • SLA
Most popular
Scale
$79/mo

For production apps with real traffic and growth.

  • 2M requests / mo
  • Batch + streaming
  • Priority inference queue
  • 99.9% SLA
  • Custom label schemas
  • Email + chat support
Enterprise
Custom

Dedicated capacity, compliance and on-prem options.

  • Unlimited volume
  • Dedicated GPU pods
  • Fine-tuned models
  • SOC2 · GDPR · HIPAA
  • 99.99% SLA
  • On-prem / VPC deploy

Ship language features
this afternoon.

Grab a free API key and make your first call in under 5 minutes.