Expand text
Feed it three bullet points and get back a paragraph that reads like someone actually wrote it. The expand text api is built for the moment when you have the facts but not the time to phrase them, and it fills in transitions, connective tissue and tone without inventing claims you didn't give it.
Run it online
Run this on our servers with your account. Free tools run in your browser; this one bills your KIT balance per the price above.
Who ends up needing this
Product teams writing release notes from a changelog, support staff turning ticket shorthand into a reply, and content pipelines that generate short summaries upstream and need a longer version downstream all hit the same wall: raw facts don't read like writing. text.expand exists for exactly that gap, taking terse input and producing fuller sentences that keep the original meaning intact, without inflating the text with claims you never made or details you never gave it.
What actually happens to your input
Send your bullets, notes or a short paragraph to POST /text/expand and the task queues immediately, returning a task_id so your application doesn't sit there waiting. The engine reads what you sent, identifies the discrete pieces of information, and writes them out as connected prose, adding the kind of linking phrases a human editor would add rather than just concatenating sentences. It also respects the order you gave your points in, since that order usually carries its own logic, whether chronological, by priority, or by cause and effect.
A format that's older than the web
Outlining and expansion are a rhetorical pair as old as composition itself: writers have long drafted skeletal notes first and prose second, whether on index cards or in a bulleted doc. This api mechanizes the second half of that habit, so the skeleton you already have becomes the draft you actually publish, without you doing the sentence-by-sentence stitching.
What you get back and when
Results arrive through a signed webhook the moment the task finishes, or you can pull them from a signed link that stays valid for 24 hours if polling suits your setup better. Either way the expanded text comes back as plain text ready to drop into a CMS, email template or document.
Where it sits in a larger pipeline
Because every call is asynchronous and identified by a task_id, text.expand slots cleanly into batch jobs: expand a thousand product bullet lists overnight, or trigger a single expansion the instant a support agent submits shorthand notes. It composes well with summarization or rewriting endpoints upstream and downstream, since the output is just text, no special format to unpack, and it costs nothing extra to wire into an existing queue that already tracks task_id values from other parts of the api.
What you can do with it
Release notes from a changelog
Convert terse commit-style bullets into a paragraph customers can actually read in a product update email.
Support macros into replies
Turn an agent's shorthand notes ('refund issued, apologized, offered discount') into a properly phrased customer response.
Outline to draft
Take a writer's bullet outline for a blog section and generate the first full-prose pass before human editing.
Meeting notes to summary
Expand clipped meeting minutes into a narrative recap suitable for stakeholders who weren't in the room.
FAQ
How does the expand text api decide what to add?
It only elaborates on the information present in your input, adding phrasing, transitions and structure, not new facts or claims.
Is there a free tier?
There's no free tier — free tiers get abused and slow everyone down. Access runs on a prepaid ForHosting KIT balance: top up from $10.00 (it never expires) and each request is charged at its published price, so a call with no balance returns HTTP 402. No subscription, no tokens, no invented credits, and a failed task is never charged.
What's the pricing?
$0.003 per request plus $0.0135 per 1,000 words processed, billed only on tasks that complete successfully.
Do I get charged if a task fails?
No. Failed tasks are retried automatically up to three times, and you're only billed once a task actually succeeds; otherwise you get a clear error.
How do I get the result?
Via a signed webhook call when the task finishes, or by fetching a signed link that stays valid for 24 hours.
Can I send bulk requests?
Yes, POST /text/expand is async and returns a task_id per call, so you can fire many requests in parallel and collect results as each webhook lands.
What languages does it support?
Any input you send is processed as-is; the engine expands in the language of the source text.
Is my text stored or used for training?
Text is retained only for the retention window needed to deliver results, then deleted, and it's never used to train models.
For developers — API access
Everything on this page is available programmatically. This section is for teams who want to wire it into their own systems; everyone else can just use the tool above.
API endpoint
Prefer to automate it? One authenticated POST creates the task; the result comes back by webhook or a signed link. The same capability also runs here on the web, and soon from our app, email and Telegram.
Call it from your stack
curl -X POST https://api.kit.forhosting.com/text/expand \
-H "Authorization: Bearer $KIT_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"…"}'const res = await fetch("https://api.kit.forhosting.com/text/expand", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.KIT_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
"text": "…"
})
});
const { task_id } = await res.json();import os, requests
res = requests.post(
"https://api.kit.forhosting.com/text/expand",
headers={"Authorization": f"Bearer {os.environ['KIT_KEY']}"},
json={
"text": "…"
},
)
task_id = res.json()["task_id"]<?php
$res = file_get_contents("https://api.kit.forhosting.com/text/expand", false, stream_context_create([
"http" => [
"method" => "POST",
"header" => "Authorization: Bearer " . getenv("KIT_KEY") . "\r\nContent-Type: application/json",
"content" => '{"text":"…"}',
],
]));
$task = json_decode($res, true);body := bytes.NewBufferString(`{"text":"…"}`)
req, _ := http.NewRequest("POST", "https://api.kit.forhosting.com/text/expand", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("KIT_KEY"))
req.Header.Set("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)Example request
{
"text": "…"
}Example response
{
"task_id": "tsk_a1b2c3d4e5f6a1b2c3d4e5f6",
"type": "text.expand",
"status": "queued",
"_links": {
"result": "/tasks/tsk_…/result"
}
}The API is asynchronous: the call returns a task_id immediately and the result arrives by webhook. Polling is capped at 1 req/s per task.
Pricing
Published price — no tokens, no invented credits. A failed task is never charged.
Limits
max_tokens | 20000 |
Errors
| HTTP | Code | Meaning |
|---|---|---|
401 | unauthorized | Missing or invalid API key. |
402 | insufficient_balance | Your balance doesn't cover the task price. |
404 | unknown_type | That task type doesn't exist. |
429 | rate_limited | Too many requests. Use the webhook instead of polling. |
422 | task_failed | The task failed after 3 retries. You are never charged for it. |