API

The Textlume writing tools, callable from your code

Post text from an app, a script or an agent and receive the same result the site shows: a detector reading with its confidence rating, a rewrite with its fact checks, a summary or a list of grammar issues.

Get a key on the dashboard Open the developer docs

Example request

curl -X POST https://textlume.com/api/v1/detect \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"On Tuesday evening the neighborhood association met to discuss the proposed bike lane on Elm Street."}'

const res = await fetch('https://textlume.com/api/v1/detect', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.API_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({
    "text": "On Tuesday evening the neighborhood association met to discuss the proposed bike lane on Elm Street."
  }),
})
const data = await res.json()
if (!res.ok) throw new Error(`${data.error.code}: ${data.error.message}`)

import os
import requests

res = requests.post(
    "https://textlume.com/api/v1/detect",
    headers={"Authorization": f"Bearer {os.environ['API_KEY']}"},
    json={
        "text": "On Tuesday evening the neighborhood association met to discuss the proposed bike lane on Elm Street.",
    },
    timeout=90,
)
data = res.json()
if not res.ok:
    raise RuntimeError(f"{data['error']['code']}: {data['error']['message']}")

What developers use it for

Review many submissions at once

One call takes up to 50 texts and returns a reading for each one, with its range and confidence rating. Useful for a moderation queue or a course platform.

Rewriting in your own editor

Humanize or paraphrase drafts from inside your product, with the fact checks the site runs. Numbers, names and quotations stay as they were.

Summaries of long reports

Reduce a report or an article to key sentences, one paragraph or a bullet list, at a length you set.

Grammar checks in your pipeline

Get each grammar, spelling and style issue with its position in the text and the replacements we suggest.

Endpoints

One key works across all 6 routes. Each route takes a POST with a JSON body and replies in JSON.

POST /api/v1/detectCheck one text
Returns the detector reading for a single text: a figure from 0 to 100, the range around it, a reading for each sentence and whether the language is calibrated.
Required scope: detectSee the reference
POST /api/v1/detect/batchCheck several texts
Send as many texts as the batch limit allows in a single call. Before it runs, the call must have enough words available for every text it could read (50 words or more per text). Words reserved for a text that returns no reading are refunded afterwards. A failure on one text does not fail the rest of the batch.
Required scope: detectSee the reference
POST /api/v1/humanizeHumanize a text
Runs the humanizer with its fact checks. Numbers, names and quotations are preserved, and if a rewrite changes a fact, it is repaired or flagged.
Required scope: rewriteSee the reference
POST /api/v1/paraphraseParaphrase a text
Runs the paraphraser, with the same modes as the paraphrasing tool on the site.
Required scope: rewriteSee the reference
POST /api/v1/summarizeSummarize a text
Runs the summarizer and returns key sentences, a paragraph or bullet points.
Required scope: summarizeSee the reference
POST /api/v1/grammarCheck grammar
Finds grammar, spelling, punctuation and style issues and returns each one with its position in the text and suggested replacements.
Required scope: grammarSee the reference

Plan and top-up packs

Pro

29.99 USD per month

50,000: humanizer words per month, plus 50,000 paraphraser words
20,000: words per call
60: requests per key in each window of 60 seconds
4 / 2: detect and rewrite calls in flight per key

Get a key on the dashboard

Top-up packs

AI detector50,000wordsfrom 5.99 USD
Humanizer10,000wordsfrom 9.99 USD
Paraphraser10,000wordsfrom 9.99 USD
Summarizer25,000wordsfrom 6.99 USD

How the API counts words

An API call uses words exactly as the site does. A humanize call draws on the humanizer words of the Pro plan, and a summarize call draws on its summarizer words. Once those are gone, humanize and paraphrase calls use your top-up words. A call that no balance can cover is rejected and nothing is charged. Each response reports the words used and the words remaining.

See every counting rule

Pro includes the API, and API calls use the same word allowance as the website. A detect call uses your plan's detector words, a humanize call its humanizer words and a summarize call its summarizer words, with no separate API allowance. Once a plan allowance is used up, detector, humanizer and paraphraser calls draw on your top-up balance, just like on the website. The other tools have no top-up balance. If the remaining words and balance together can't cover a call, it's refused with a 402 and costs nothing. Every successful response shows the words used, where they came from and what's left, unless recorded is false. API use for an account stops at 250,000 words per billing period whatever the balance, so a leaked key can't use up everything at once.

Limits

60requests per key in each window of 60 seconds
4detect calls in flight per key
2humanize, paraphrase or summarize calls in flight per key
50texts per batch
20,000words per call
5active keys per account

Each call accepts up to 20,000 words, whether you send one text or a whole batch.
On every plan, the detector reads a single text of up to 90,000 characters, which is roughly 10,000 words. Longer texts get a 413 text_too_long response, even when the call is within its word limit.
When the engines are under load, Pro users on the site are served ahead of API calls, so an API call may have to wait.

MCP server

The same tools for your AI agent

With the MCP server, an agent in Claude Desktop, Claude Code or Cursor gets six tools. The server only calls this API with your key, so the agent sees the same reading as the site.

MCP server setup A ready-made skill for Claude

detect_textChecks one text.
detect_batchChecks several texts.
humanize_textHumanizes a text and runs the fact checks.
paraphrase_textParaphrases a text.
summarize_textSummarizes a text.
check_grammarChecks grammar and spelling.

Get an API key

Get a key on the dashboard Open the developer docs

This page does not create keys.