ForHosting KIT · Text & AI

Content ideas

A blank content calendar is the most expensive thing a marketing team owns. This endpoint takes a single seed — a topic, a product, an audience — and returns a structured month of distinct angles, headlines and formats, so the only decision left is which one to write first.

● StablePer request + per batch$0.003

Run — $0.003 + $0.0135/batch How it works & API

Use it from WebAPIEmailApp soonTelegram soon

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.

Built for the person who owns the calendar

Whoever is responsible for keeping a blog, newsletter or social feed alive knows the real bottleneck is rarely writing — it's deciding what to write about without repeating last quarter's ideas. This endpoint is built for that person: content leads, solo founders, agencies juggling several clients, or a growth team that needs a defensible plan before a stakeholder meeting.

What you send, what comes back

You POST a seed topic plus optional context — audience, tone, industry, competitors to differentiate from, formats you already publish. The task runs asynchronously and returns a structured set of ideas: a working title, a one-line angle, a suggested format (guide, comparison, case-style post, listicle, video script outline), and a short note on why that angle fits the seed. Nothing arrives as a wall of undifferentiated text.

Why 'ideas', not 'articles'

Idea generation and full drafting are different jobs with different failure modes. A generated article that reads badly is expensive to fix; a generated idea that misses is free to discard. Separating the two lets teams keep human judgment where it earns its keep — choosing and refining — while automating the part that mostly involves staring at a blank page.

A short note on where this comes from

Editorial calendars as a discipline grew out of newsrooms, where beat reporters and desk editors planned coverage weeks ahead to avoid duplicate stories and dead air. Content marketing borrowed the format without borrowing the staff, which is exactly the gap this endpoint fills — the planning discipline of a newsroom, sized for a team of one or a hundred.

Where it sits in a pipeline

Because the response is structured JSON, ideas drop straight into a backlog, a spreadsheet, or a task in your project tool via webhook, ready to be assigned, scheduled or scored before anyone opens a document. Teams that pair it with our writing or SEO endpoints go from seed to scheduled draft without a manual handoff in between.

What you can do with it

Monthly editorial planning

A two-person marketing team feeds in their product category once a month and gets enough distinct angles to fill the calendar without repeating themselves.

Agency client kickoffs

An agency generates a first-pass idea list per client seed to open the planning call with options instead of a blank slide.

Seasonal and campaign bursts

A seed like 'back-to-school' or 'year-end review' returns a batch of angles tied to that window, ready to slot into a launch calendar.

Breaking a content rut

A blog that has been circling the same three topics for months uses the endpoint to surface angles the team hadn't considered.

FAQ

How does the content idea generator API work?

You send a seed topic and optional context to POST /text/content-ideas, the task runs asynchronously, and you get back a structured batch of titles, angles and formats via webhook or a signed link.

Is there a free tier or free trial?

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.

How many ideas do I get per request?

Ideas are returned as a batch sized to a typical month of publishing; exact counts depend on the parameters you send in the request.

What format is the output in?

Structured JSON with a title, angle, suggested format and rationale per idea, so it can be piped directly into a calendar or backlog tool.

Do I get charged if a task fails?

No. Failed tasks are retried automatically up to three times and are never charged; you only pay for ideas that were actually generated and delivered.

Can I generate ideas for a very niche or technical topic?

Yes — the seed can be as specific as a product feature or an industry sub-segment; the more context you provide, the more targeted the angles.

How is this different from just asking a chatbot?

The endpoint returns structured, batch-ready output built for pipelines and webhooks, with predictable pricing per request and per batch instead of a one-off chat reply.

How long are results available after generation?

Results are delivered by signed webhook or via a signed link valid for 24 hours, after which the underlying data is deleted and never used for training.

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

POSThttps://api.kit.forhosting.com/text/content-ideas

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/content-ideas \
  -H "Authorization: Bearer $KIT_KEY" \
  -H "Content-Type: application/json" \
  -d &#39;{"input":"…"}'

const res = await fetch("https://api.kit.forhosting.com/text/content-ideas", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.KIT_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "input": "…"
  })
});
const { task_id } = await res.json();

import os, requests

res = requests.post(
    "https://api.kit.forhosting.com/text/content-ideas",
    headers={"Authorization": f"Bearer {os.environ[&#39;KIT_KEY']}"},
    json={
    "input": "…"
},
)
task_id = res.json()["task_id"]

<?php
$res = file_get_contents("https://api.kit.forhosting.com/text/content-ideas", false, stream_context_create([
  "http" => [
    "method"  => "POST",
    "header"  => "Authorization: Bearer " . getenv("KIT_KEY") . "\r\nContent-Type: application/json",
    "content" => &#39;{"input":"…"}',
  ],
]));
$task = json_decode($res, true);

body := bytes.NewBufferString(`{"input":"…"}`)
req, _ := http.NewRequest("POST", "https://api.kit.forhosting.com/text/content-ideas", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("KIT_KEY"))
req.Header.Set("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)

Example request

{
  "input": "…"
}

Example response

{
  "task_id": "tsk_a1b2c3d4e5f6a1b2c3d4e5f6",
  "type": "text.content_ideas",
  "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

Per request$0.003

Per batch$0.0135

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.

Read the full KIT documentation →