AI Module

The INCLUXA AI module provides nine content transform functions powered by Claude. Each function is designed for accessibility use cases: reducing reading level, generating image descriptions, scaffolding learning support, and adapting content for different learning needs.

Note

AI is a credit-pool add-on that stacks on any paid base plan (Solo, Starter, Pro, Schools, or Enterprise). Free-tier tenants cannot enable the AI module. Pick a credit-pool tier from your Billing page; unused credits do not roll over. Usage is visible in the Portal under Billing → AI module. Schools-tier AI calls are additionally governed by your signed SchoolDpaAgreement: PII is scrubbed before any prompt leaves INCLUXA, and Schools-tier data handling is governed by your DPA exhibit. See the DPA.

Credit-pool tiers

Each monthly tier grants a pool of credits that AI tasks draw from. You can change tiers at any time — changes are prorated by Stripe. Enterprise contracts may negotiate custom pool sizing.

Tier	Price (USD)	Credits / month	Good for
Lite	$29/mo	2,000	Small sites, ~2K Haiku tasks or ~130 Opus tasks / month
Plus	$59/mo	5,000	Mid-size sites, mixed Haiku + Sonnet workloads
Max	$99/mo	10,000	Content-heavy sites and edtech classrooms
Scale	$179/mo	30,000	Enterprise volume; custom negotiated above this tier

Smart Mode — pick your Claude model per task

Every transform accepts an optional mode parameter that selects which Claude tier runs the request. Credits are consumed as a multiplier of the Standard cost:

Mode	Claude model	Credits per task	When to use
Standard (0)	Haiku 4.5	1	Default. Simplify, alt-text, vocabulary, syllable break — ~95% of tasks.
Smart (1)	Sonnet 4.6	3	Translation, picture dictionaries, nuanced rephrasing.
Genius (2)	Opus 4.7	15	Hard reasoning only — equation speech, long-form summaries, tone.

Your tenant has a Smart Mode cap set by the owner. Requests above the cap return403 SmartModeCapExceeded without consuming credits. Default cap is Standard.

Sending Smart Mode via the API

# Simplify with Sonnet (3 credits instead of 1)
curl -X POST https://api.incluxa.com/api/v1/content/simplify \
  -H "X-Api-Key: inc_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "...",
    "targetGradeLevel": 5,
    "mode": 1
  }'

Overage

If you exhaust your monthly pool, further tasks are billed as metered overage at $0.02 per credit. Your current usage is shown in the Portal under Billing → AI module. To use more credits at a lower effective rate, move to a larger credit-pool tier.

Cache & free hits

All AI responses are cached by a SHA-256 hash of (content + transform + target level + mode)for 7 days. Cache is partitioned by Smart Mode tier, so Haiku and Opus outputs never mix. Cache hits return wasCached: true and consume zero credits. Building cache-friendly requests (stable input text, same grade level, same mode) maximises hit rate.

Currency & billing

AI credit-pool and any overage are always billed in USD via Stripe, globally, the same as base plans. AI pricing stays uniform worldwide and avoids FX drift on metered usage.

Available transforms

Function	API endpoint	Description
simplify()	POST /content/simplify	Rewrites text to a target reading grade level.
generateAltText()	POST /content/alt-text	Generates descriptive alt text for an image URL.
getHints()	POST /content/hints	Returns scaffolded hints for a question without revealing the answer.
rephrase()	POST /content/rephrase	Rephrases a question/answer pair for clarity or reading level.
extractVocabulary()	POST /content/vocabulary	Identifies key vocabulary words from a passage.
summarize()	POST /content/summarize	Summarizes a passage to a target length.
translate()	POST /content/translate	Translates text to a target language.
checkGrammar()	POST /content/grammar	Checks grammar and returns corrections with explanations.
extractImageText()	POST /content/ocr	Extracts all text from an image URL (OCR).

Response format

All AI transform endpoints return the same structure:

{
  "result": "...",     // the transformed content
  "wasCached": false,  // true if served from cache
  "tokensUsed": 84     // Claude tokens consumed (0 if cached)
}

Usage examples

Via React SDK

import { simplify, generateAltText, getHints } from '@incluxa/a11y-sdk'
import { useA11y } from '@incluxa/a11y-sdk'

function ContentCard({ passage, image, question, answer }) {
  const { client } = useA11y()

  // Simplify reading level
  const simple = await simplify(client, {
    text: passage,
    targetGradeLevel: 5,
  })

  // Generate alt text
  const alt = await generateAltText(client, {
    imageUrl: image,
    context: 'Science textbook diagram',
  })

  // Get hints without revealing the answer
  const hints = await getHints(client, {
    question,
    correctAnswer: answer,
    gradeLevel: 7,
    subject: 'math',
  })
}

Via Vanilla JS SDK

import { IncluxaA11y } from '@incluxa/a11y-sdk'

const a11y = new IncluxaA11y({ apiKey: 'inc_live_YOUR_KEY' })
await a11y.mount()

const simplified = await a11y.simplify(longPassage, 5)
const altText = await a11y.generateAltText(imageUrl, 'Context hint')
const hints = await a11y.getHints(question, answer, { gradeLevel: 8 })

Via REST API directly

# Translate to Spanish
curl -X POST https://api.incluxa.com/api/v1/content/translate \
  -H "X-Api-Key: inc_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to today\'s lesson on fractions.",
    "targetLanguage": "es"
  }'

# OCR — extract text from image
curl -X POST https://api.incluxa.com/api/v1/content/ocr \
  -H "X-Api-Key: inc_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "imageUrl": "https://example.com/worksheet.png"
  }'

Monthly AI quota

Credit-pool tier	Credits / month	Price (USD)
Lite	2,000	$29/mo
Plus	5,000	$59/mo
Max	10,000	$99/mo
Scale	30,000	$179/mo

Important

Cached responses do not use credits from your pool. Building cache-friendly requests (consistent input text, same grade level) maximises cache hit rate and reduces costs.