Generate a Snackable Read

curl --request POST \
  --url https://api.webless.ai/api/v1/snackable-read \
  --header 'Content-Type: application/json' \
  --data '
{
  "company": "YOUR_COMPANY",
  "canonical_url": "https://example.com/articles/product-launch"
}
'

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    company: 'YOUR_COMPANY',
    canonical_url: 'https://example.com/articles/product-launch'
  })
};

fetch('https://api.webless.ai/api/v1/snackable-read', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.webless.ai/api/v1/snackable-read"

payload = {
    "company": "YOUR_COMPANY",
    "canonical_url": "https://example.com/articles/product-launch"
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

{
  "status": "ready",
  "bullets": [
    "The launch introduces a faster setup flow.",
    "Existing integrations remain compatible.",
    "The new experience is available to all customers."
  ],
  "source_url": "https://example.com/articles/product-launch",
  "title": "Product launch",
  "cache_status": "miss",
  "version": "published",
  "resolved_version": "published",
  "resolved_corpus_version": 12,
  "generated_at": "2026-06-12T19:30:00+00:00"
}

POST

api

snackable-read

Generate a Snackable Read

curl --request POST \
  --url https://api.webless.ai/api/v1/snackable-read \
  --header 'Content-Type: application/json' \
  --data '
{
  "company": "YOUR_COMPANY",
  "canonical_url": "https://example.com/articles/product-launch"
}
'

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    company: 'YOUR_COMPANY',
    canonical_url: 'https://example.com/articles/product-launch'
  })
};

fetch('https://api.webless.ai/api/v1/snackable-read', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.webless.ai/api/v1/snackable-read"

payload = {
    "company": "YOUR_COMPANY",
    "canonical_url": "https://example.com/articles/product-launch"
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

{
  "status": "ready",
  "bullets": [
    "The launch introduces a faster setup flow.",
    "Existing integrations remain compatible.",
    "The new experience is available to all customers."
  ],
  "source_url": "https://example.com/articles/product-launch",
  "title": "Product launch",
  "cache_status": "miss",
  "version": "published",
  "resolved_version": "published",
  "resolved_corpus_version": 12,
  "generated_at": "2026-06-12T19:30:00+00:00"
}

Generate a short set of takeaways from content already indexed for a page. Use the page’s canonical URL to identify the content.

Send URL context only. Do not send the full page body from the browser. The API returns not_found when the page is not available in the selected index.

Choose generation behavior

Goal	Field
Return between one and six takeaways	Set `max_bullets`. The default is `3`.
Adjust the writing style	Set `tone` to `neutral`, `warm`, `professional`, or `concise`.
Keep existing takeaways	Pass up to five strings in `existing_bullets`. They count toward `max_bullets`.
Test unpublished runtime changes	Set `version` to `unpublished`. Production requests default to `published`.
Bypass the cache and summary analytics	Set `is_private_session` to `true` or `tracking_consent` to `false`.

In a private session, the API rewrites existing_bullets in the requested tone. In a non-private session, it preserves them and generates only the remaining bullets.

Handle the response status

The endpoint returns HTTP 200 for each application-level result.

Status	Meaning
`ready`	`bullets` contains the generated takeaways.
`not_found`	The page is not in the selected index. `bullets` is empty.
`error`	The API could not produce usable takeaways.

The legacy POST /api/v1/quick-read route remains compatible. Use POST /api/v1/snackable-read for new integrations.

Body

application/json

company

string

required

Public company or index identifier.

canonical_url

string

required

Canonical URL of the page to summarize.

page_url

string

Current browser URL. Optional; fragments and tracking params are normalized server-side.

title

string

Optional page title for display and prompt context.

locale

string

Optional locale or language hint.

requestId

string

Caller-generated request identifier.

sessionId

string

Caller-generated session identifier.

is_private_session

boolean

default:false

When true, bypasses the cache and summary analytics logging.

Tracking consent for this request. Setting this to false also enables private-session behavior.

model

string

default:gpt

Model alias configured for the runtime package.

version

enum<string>

default:published

Runtime package pointer. Omit this field or use published for production traffic. Use unpublished only when testing an unpublished runtime package.

Available options:

published,

unpublished

max_bullets

integer

default:3

Maximum number of Snackable Read bullets to return.

Required range: 1 <= x <= 6

tone

enum<string> | null

Writing style for generated bullets.

Available options:

neutral,

warm,

professional,

concise

existing_bullets

string[] | null

Existing bullets to preserve or rewrite. These count toward max_bullets.

Maximum array length: 5

Response

Snackable Read result for the supplied page URL

status

enum<string>

required

Snackable Read generation status.

Available options:

ready,

not_found,

error

bullets

string[]

required

Concise page takeaways. Empty when status is not_found or error.

cache_status

enum<string>

required

Whether the response came from cache.

Available options:

hit,

miss,

bypass

source_url

string | null

Normalized source URL used for lookup.

title

string | null

Page title returned by the request or indexed content.

version

enum<string>

default:published

Runtime package pointer. Omit this field or use published for production traffic. Use unpublished only when testing an unpublished runtime package.

Available options:

published,

unpublished

resolved_version

string | null

Resolved runtime pointer after fallback handling.

resolved_corpus_version

integer | null

Resolved indexed corpus version used internally for the response.

generated_at

string<date-time> | null

Server timestamp for the generated response.

Overview

Search API

Page content API

Session API

Data API

Generate a Snackable Read

Choose generation behavior

Handle the response status

Body

Response

​Choose generation behavior

​Handle the response status

Body

Response

Choose generation behavior

Handle the response status