How many images can I generate in one call?

Up to 10 items per call, over REST or MCP alike; each item counts as one render. For thousands of images loop the batch call, or queue /render/async with a webhook.

Can I generate images from a CSV file?

Yes: read rows with any language or no-code tool (n8n, Make, Zapier) and map columns to template variables. An AI agent connected over MCP can do the mapping for you.

Do all images share the same design?

They share the template: layout, fonts, brand colors stay fixed while variables change. Need several designs? Templates are cheap; you start with 20 template slots.

How is this different from a script with Photoshop or Canva?

No desktop software, no per-seat license, no manual export. Templates are JSON, renders are HTTP calls, output is deterministic; it fits CI, cron and agent pipelines.

Batch image generation from one template

A conference needs 300 personalized badges. A store updates 80 price tags every Friday. A newsletter wants a branded header per issue. That is not a design problem; it is a data problem. In Rendry you design (or let your AI agent design) one template with {variables}, then feed it rows of data: each render swaps names, prices, photos, QR codes and returns a finished PNG.

One call renders up to 10 personalized images: POST /render/batch over REST, or the render_batch tool if your agent speaks MCP. For longer queues, /render/async with a webhook. Every image is deterministic: same layout, same brand, different data.

Start free; 50 credits included · Documentation

Why teams and agents use it

Variables everywhere. Text, image URLs, QR/barcode content: anything can be a {variable} filled per item.
Built-in batching. One template, a list of dynamic_data sets, per-item filenames: up to 10 images per call, each in ~1-3 s. The same call over REST (POST /render/batch) and over MCP (render_batch).
From any data source. CSV via a script, Airtable/Sheets via n8n, Make or Zapier HTTP modules, or an AI agent that reads your data and drives MCP.
Personalization that scales. Start with 50 free credits; $79 buys 25,000 credits. No per-seat pricing.

One request, one image

curl -X POST https://rendry.io/api/v1/render/batch \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "preset_id": "conference-badge",
    "items": [
      {"dynamic_data": {"name": "Ada Lovelace", "role": "Speaker"}, "filename": "badge-ada.png"},
      {"dynamic_data": {"name": "Alan Turing",  "role": "Keynote"}, "filename": "badge-alan.png"}
    ]
  }'

# Up to 10 per call. Want to see the design first? POST /render/preview costs 0.1 credits.

Ready-made templates for this

Conference Badge: Attendee badge with name, role and company. Use for: conferences and meetups. (600x900)
Certificate: 1400x990 certificate. Cream-gold pastel mesh, thin gold frame, gold gradient serif name, blob seal with star. Mood: premium diploma. Use for: courses, awards, achievements. (1400x990)
Price Tag: Shelf price tag with product name and big price. Use for: retail shelves and markets. (500x300)
Event Ticket with Barcode: Event ticket with barcode, seat and date fields. Use for: tickets and passes. (1200x500)
We're Hiring Card: Square hiring post. Teal-blue mesh, gradient role headline, mono chips for stack/salary/mode. Mood: modern tech employer. Use for: job openings. (1080x1080)
Restaurant Menu Item: Menu item card with photo, name and price. Use for: cafe/restaurant menus and food delivery. (800x1000)

Built for AI agents first

Rendry ships a native remote MCP server (https://rendry.io/api/v1/mcp) with 32 tools. Your agent designs the templates itself, previews drafts cheaply, then renders batches — nobody has to lay anything out by hand. Full control over every pixel stays with the agent, while a human can always open the same template in the visual editor and adjust it. No headless browser, no screenshot hacks, no glue code.

Machine-readable: llms.txt · llms-full.txt · openapi.json · mcp.json

Frequently asked questions

How many images can I generate in one call?: Up to 10 items per call, over REST or MCP alike; each item counts as one render. For thousands of images loop the batch call, or queue /render/async with a webhook.
Can I generate images from a CSV file?: Yes: read rows with any language or no-code tool (n8n, Make, Zapier) and map columns to template variables. An AI agent connected over MCP can do the mapping for you.
Do all images share the same design?: They share the template: layout, fonts, brand colors stay fixed while variables change. Need several designs? Templates are cheap; you start with 20 template slots.
How is this different from a script with Photoshop or Canva?: No desktop software, no per-seat license, no manual export. Templates are JSON, renders are HTTP calls, output is deterministic; it fits CI, cron and agent pipelines.