ModelFold PPT 1.1

A model built by ModelFold. Send a topic (optionally with notes, facts or an article) and get back a complete, editable presentation:

an outline first, then every slide written in batches so the deck stays coherent;
6–50 slides in 10 layouts: cover, agenda, section divider, bullets, two columns, image + text, big numbers, quote, timeline, closing;
6 themes (midnight / corporate / paper / forest / sunset / mono) with shared palette, fonts, page numbers, footer and logo area on every slide;
optional AI images, generated only for layouts that need them;
output as PPTX (text boxes and shapes are native, editable PowerPoint objects), PDF, PNG (ZIP) and the Studio document JSON;
every deck is saved to the caller's Studio; the returned studio_url opens it for further editing.

Overview

Field	Value
Model ID	`modelfold-ppt-1.1`
Type	Office / presentation (`document`)
Protocol	Async jobs: `POST /api/v1/jobs/createTask` + `GET /api/v1/jobs/recordInfo`
Auth	`Authorization: Bearer <API key>`
Latency	Usually 30–90 seconds; longer with AI images
File retention	30 days (same as other generated files)

Pricing

Price per deck = base + per-slide price × slides + per-image price × images actually generated.

Item	Default (credits)
Base per deck	3
Per slide	0.5
Per AI image	6 (= the site's image-model price + 1; follows the markup setting)

Credits for the maximum possible number of images (min(12, ceil(slides × 0.4))) are reserved when the task is created and settled to the images actually generated; failed tasks are refunded in full. Examples: 8 slides without images, 7 credits; 10 slides with 4 images, 32 credits. See the model page for current prices.

Parameters (inside `input`)

Name	Type	Required	Default	Description
`prompt`	string	Yes	—	Topic or one-sentence brief, 2–1000 characters. Alias: `topic`.
`content`	string	No	—	Source material: notes, facts or an article, up to 20000 characters. Alias: `notes`.
`slides`	integer	No	`10`	Number of slides, 6–50.
`language`	string	No	`en`	Text language: `zh` `en` `ja` `es` `ko` `fr` `de` `pt`.
`theme`	string	No	`midnight`	`midnight` `corporate` `paper` `forest` `sunset` `mono`.
`template`	string	No	—	Own template ID or public design ID. Overrides the selected built-in theme.
`ai_images`	boolean	No	`true`	Generate AI images (billed per generated image).
`output_formats`	string[]	No	`["pptx"]`	Any of `pptx`, `pdf`, `png` (ZIP with one PNG per slide), `json` (Studio document).

Optional top-level callBackUrl + callbackSecret (completion callback) and the Idempotency-Key header work exactly as for other async models; see Async jobs.

Request examples

bash

curl -X POST https://ai.modelfold.online/api/v1/jobs/createTask \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "modelfold-ppt-1.1",
    "input": {
      "prompt": "Quarterly business review for our AI video product",
      "content": "Q3 revenue +38%, 12k paying users, NPS 64; next quarter: international and enterprise",
      "slides": 10,
      "language": "en",
      "theme": "corporate",
      "template": "TEMPLATE_ID",
      "ai_images": true,
      "output_formats": ["pptx", "pdf"]
    }
  }'
# {"code":200,"msg":"success","data":{"taskId":"…","state":"queued","credits":27}}

curl "https://ai.modelfold.online/api/v1/jobs/recordInfo?taskId=TASK_ID" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY"

python

import os, time, json, requests

API = "https://ai.modelfold.online/api/v1/jobs"
H = {"Authorization": f"Bearer {os.environ['MODELFOLD_API_KEY']}"}

task = requests.post(f"{API}/createTask", headers=H, json={
    "model": "modelfold-ppt-1.1",
    "input": {"prompt": "Onboarding training for new sales hires", "slides": 8, "theme": "paper", "template": "TEMPLATE_ID", "ai_images": False},
}).json()["data"]

while True:
    job = requests.get(f"{API}/recordInfo", headers=H, params={"taskId": task["taskId"]}).json()["data"]
    if job["state"] in ("success", "fail"):
        break
    time.sleep(5)

result = json.loads(job["resultJson"])["resultObject"]
open("deck.pptx", "wb").write(requests.get(result["files"]["pptx"]).content)

const API = 'https://ai.modelfold.online/api/v1/jobs'
const headers = { Authorization: `Bearer ${process.env.MODELFOLD_API_KEY}`, 'Content-Type': 'application/json' }
const { data: task } = await fetch(`${API}/createTask`, { method: 'POST', headers,
  body: JSON.stringify({ model: 'modelfold-ppt-1.1', input: { prompt: 'Coffee shop launch plan', slides: 8 } }) }).then((r) => r.json())
let job
do {
  await new Promise((r) => setTimeout(r, 5000))
  job = (await fetch(`${API}/recordInfo?taskId=${task.taskId}`, { headers }).then((r) => r.json())).data
} while (!['success', 'fail'].includes(job.state))
console.log(JSON.parse(job.resultJson).resultObject.files.pptx)

Response

When state is success, resultJson is a JSON string: resultUrls lists every generated file and resultObject holds the structured result:

json

{
  "title": "AI Video Product QBR",
  "slides": 10,
  "theme": "corporate",
  "language": "en",
  "template": "123",
  "files": { "pptx": "https://…/modelfold-ppt-….pptx", "pdf": "https://…/modelfold-ppt-….pdf" },
  "cover_url": "https://…/modelfold-ppt-…-cover.jpg",
  "studio_url": "https://ai.modelfold.online/studio/edit/123",
  "design_id": 123,
  "ai_images": { "requested": true, "generated": 3 },
  "outline": [{ "index": 1, "type": "cover", "title": "…", "points": ["…"] }],
  "billing": { "credits": 26, "base": 3, "per_slide": 0.5, "per_image": 6 }
}

Field	Description
`files.pptx` / `files.pdf` / `files.png_zip` / `files.json`	Files for the requested `output_formats`
`studio_url`	Open the deck in ModelFold Studio (only the API key owner can open it)
`outline`	Slide types, titles and key points
`ai_images`	Requested / generated AI images
`billing`	Final credits and breakdown (matches `usage.credits`)

On failure state is fail, failMsg explains why, and the reserved credits are refunded in full.

All models
Async jobs
Try it online: AI Design Studio · Full slide deck

Optional uploaded template

Upload a PPTX (up to 12 MB) using POST /v1/studio/templates/upload with the same API key and JSON { "name": "brand.pptx", "data": "BASE64_PPTX" }. The response contains template_id. Pass "template": "123" inside input to use it, a saved Studio template, or a public design ID. Private templates require ownership. Uploaded originals are never publicly served. Basic theme colors, fonts, backgrounds, logos and text layouts are imported; complex charts, groups, animation and unsupported media are simplified or omitted, and missing fonts fall back. Review before use.

Long outlines are generated in chunks of up to 10 slides; slide content uses batches of 4, up to 3 concurrently. Allow several minutes for 50 slides. AI images are capped at 12. PDF rendering runs one page at a time to bound image memory.

Template IDs and image style

Uploading does not call a model. Use the same API key to create a deck and set input.template to the returned template_id string. It overrides theme; private templates are owner-only.

GET /v1/studio/templates (authenticated): list your templates.
GET /v1/studio/templates/public (anonymous): list real public/official IDs. Response: {"ok":true,"templates":[{"id":"123","title":"…","format":"slide","preview_url":null}]}. The list may be empty; query it instead of inventing official IDs.
POST /v1/studio/templates/upload (authenticated): JSON name is a .pptx filename; data is plain Base64 without a data: prefix, maximum 12 MB. Response: {"ok":true,"template_id":"123","warnings":["pptx_simplified","font_fallback"],"design":{…}}. The original PPTX is not publicly downloadable.
OOXML supplies palette, fonts, basic text geometry and master artwork. The existing billed slide call inspects up to two non-logo images for photography/illustration/flat/3D medium, lighting, composition and background texture, then explicitly includes that style in each imagePrompt. The same template mapping applies typography and basic layouts.
Image generation prefers a reference-capable sibling (Seedream 5 Flash image-to-image or Nano Banana 2 Lite), sending up to two template images. Extracted assets are retained in uploads/studio; the original file stays private. Without artwork or model support, style is text-only; pixel-identical reproduction is not guaranteed. Complex charts/groups/animations and unavailable fonts are simplified.
ai_images=false generates and bills no images. Only successful images are billed, capped at min(12, ceil(slides × 0.4)). Vision is part of the existing billed slide call, with no separate analysis call. Result template echoes the ID, or null when omitted.

bash

# Inspect public IDs, then upload a private template (Python avoids shell Base64 differences).
curl https://ai.modelfold.online/v1/studio/templates/public
python3 -c 'import base64,json; print(json.dumps({"name":"brand.pptx","data":base64.b64encode(open("brand.pptx","rb").read()).decode()}))' > template.json
curl https://ai.modelfold.online/v1/studio/templates/upload \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" -H "Content-Type: application/json" --data-binary @template.json
curl https://ai.modelfold.online/v1/studio/templates -H "Authorization: Bearer $MODELFOLD_API_KEY"
# Use returned template_id in input.template in the createTask examples above.

python

import base64, os, requests
base = "https://ai.modelfold.online"
headers = {"Authorization": "Bearer " + os.environ["MODELFOLD_API_KEY"]}
public = requests.get(base + "/v1/studio/templates/public").json()["templates"]
with open("brand.pptx", "rb") as f:
    uploaded = requests.post(base + "/v1/studio/templates/upload", headers=headers,
        json={"name": "brand.pptx", "data": base64.b64encode(f.read()).decode()})
uploaded.raise_for_status()
template_id = uploaded.json()["template_id"]
response = requests.post(base + "/api/v1/jobs/createTask", headers=headers,
    json={"model": "modelfold-ppt-1.1", "input": {"prompt": "Brand launch plan",
          "slides": 6, "template": template_id, "ai_images": True, "output_formats": ["pptx", "json"]}})
response.raise_for_status()
print(response.json())  # Poll recordInfo as above; check state=success before reading resultJson.

import { readFile } from 'node:fs/promises'
const base = 'https://ai.modelfold.online'
const headers = { Authorization: `Bearer ${process.env.MODELFOLD_API_KEY}`, 'Content-Type': 'application/json' }
const publicTemplates = await fetch(base + '/v1/studio/templates/public').then(r => r.json())
const upload = await fetch(base + '/v1/studio/templates/upload', { method: 'POST', headers,
  body: JSON.stringify({ name: 'brand.pptx', data: (await readFile('brand.pptx')).toString('base64') }) })
if (!upload.ok) throw new Error(await upload.text())
const { template_id } = await upload.json()
const task = await fetch(base + '/api/v1/jobs/createTask', { method: 'POST', headers,
  body: JSON.stringify({ model: 'modelfold-ppt-1.1', input: { prompt: 'Brand launch plan',
    slides: 6, template: template_id, ai_images: true, output_formats: ['pptx', 'json'] } }) }).then(r => r.json())
console.log(task) // Poll recordInfo as above; check state=success before reading resultJson.

ModelFold PPT 1.1 ​

Overview ​

Pricing ​

Parameters (inside input) ​

Request examples ​

Response ​

Related ​

Optional uploaded template ​

Template IDs and image style ​