Skip to content
Catalog

cn8/text-summarize

Send a piece of text and get back a concise summary, the individual sentences that

Learn more about Text Summarization
Text NLPsyncInstant previewtextanalysisnlp

Try it

Document to summarize

Result

Results show up here

The sample input is ready — just hit Run.

Overview

Send a piece of text and get back a concise summary, the individual sentences that make up that summary, and a compression ratio showing how much shorter the result is. Responses are synchronous — one request, one result. Ideal for article digests, executive summaries and content previews.

Key capabilities

Summary + sentence list

Get both the joined summary text and the individual sentences it was assembled from, on every call.

Compression ratio

The ratio of summary length to original length (e.g. 0.6 means the summary is 60% of the original).

No tuning required

Send just the text. A sensible summary length is chosen for you automatically.

Multilingual

Works across many languages out of the box.

When to use it

News digests

Summarize articles for daily or weekly email digests.

Report compression

Create executive summaries from long documents or meeting notes.

Content preview

Generate short previews for articles, papers, or product descriptions.

Input & output

input

A single text to summarize.

JSON body

output

The summary, the sentences it was built from, and the compression ratio.

JSON

Guides & tips

How it works

  • Your text is condensed into a short summary made up of its most important sentences.
  • summary is the ready-to-display summary string; sentences lists those same sentences individually.
  • compression_ratio tells you how much shorter the summary is than the original (e.g. 0.6 = 60% of the original length).

Tips

  • Send a single text per request in the text field. To summarize many, call the endpoint once per text.
  • Use summary for display, and sentences when you want to render the summary as a bullet list.
  • For a length-controlled or styled summary (e.g. "summarize in 50 words"), use LLM Completions with a custom prompt.

Specs

Latency
Typically 1–5 seconds depending on text length
Async
false
Rate Limit
Per API key
Max Input
A few thousand characters per text; very long inputs are trimmed automatically

Schema

Request body

textrequiredstring

The text to summarize. Send one text per request.

Response

summarystring

The condensed summary text.

sentencesarray<string>

The individual sentences that make up the summary, in order.

compression_rationumber

Length of the summary divided by the length of the original text.

Pricing

Billed per request.

ServiceUnitPrice
Text Summarizationitem$0.006/request

FAQ

Related models