Rendry: template-based image and PDF rendering

Design a template once, visually or through an external AI client; then every row of your data comes back as a finished file: a PNG, JPEG or WebP picture, a PDF of up to 20 pages whose tables continue across pages with the header row repeated, or one self-contained HTML page. Call it by REST API, the native remote MCP server (https://rendry.io/api/v1/mcp, 33 tools), a CSV batch or a public link. Deterministic output: exact layout, brand colors, legible text, scannable QR and barcodes.

Rendry renders structured templates and supplied data; the rendering pipeline does not run a generative image model. External AI clients can supply layouts and copy through MCP. Separate ML tools remove backgrounds from existing images or, when enabled, cut out an object selected by description or point.

Pricing

  • Every new account starts with 50 free credits, no credit card. A final image costs 1-3 credits by canvas size, a draft preview 0.1. A standard PDF or HTML document costs 2 credits for up to 20 pages; each further started block of 20 pages adds 1 credit. Large pages flattened entirely to pixels can add a compute surcharge; a free dry run quotes the exact cost.
  • 500 credits: $15 one-time, no subscription
  • 2,500 credits: $35 one-time, no subscription
  • 25,000 credits: $79 one-time, no subscription
  • 100,000 credits: $199 one-time, no subscription

Platform

  • Rendering for Agents: Connect an external AI agent through MCP to design templates and render images or PDFs from data. Visual editor, REST API, 50 free credits to start.
  • Image API: REST image generation API: POST a template ID + variables, get a pixel-perfect PNG in ~1-3 s. Sync and async, webhooks, OpenAPI, native MCP. Free credits to start.
  • Batch Generation: Batch image generator: feed names, prices or SKUs into one template and render hundreds of personalized images via API. render_batch, webhooks, ~1-3 s each.

Use cases

Resources

Frequently asked questions

Can Rendry convert HTML to PDF or generate animation?
HTML-to-PDF conversion, animated GIF and video output are not offered. Rendry accepts editable JSON templates and supplied data, then produces static PNG, JPEG, WebP, PDF or self-contained HTML output. Create a template in the editor, send JSON pages to POST /api/v1/render/document, or use MCP render_document.
How does Rendry create an image or document?
Rendry renders a structured template with your text, images and data. An external AI client can supply layouts or copy through MCP; the rendering pipeline does not run a generative image model. Separate ML tools remove backgrounds from existing images or, when enabled, cut out an object selected by description or point.
How does my AI agent connect?
One URL. claude.ai: add a custom connector with the MCP endpoint (https://rendry.io/api/v1/mcp) and sign in via OAuth. Claude Code, Cursor, Codex and any MCP client: same URL plus an API key. The agent gets 33 tools, from template gallery to raw-DSL design with cheap draft previews.
What keeps the agent from burning my credits while designing?
Saved test keys produce free, watermarked renders under the same validation and limits; paid external ML tools are refused in test mode. With a live key, a draft preview costs 0.1 credits — a tiny fraction of a final render. The agent iterates on preview_preset with text-fit metrics and an optional debug overlay. Render and image-processing operations are charged separately at their stated prices.
Can I fix what the agent designed?
Always. Agent-made templates are regular presets: open them in the drag-and-drop editor, nudge layers, change fonts, save. The agent keeps rendering the adjusted version.
Can Rendry make PDF documents?
Yes. The same templates render to PDF or to one self-contained HTML file, up to 20 pages a document. A table filled from rows of data continues on the next page with its header row repeated, and page numbers, a clickable contents, form fields, signature lines, bleed and crop marks are built in. A standard PDF or HTML document costs 2 credits for up to 20 pages; each further started block of 20 pages adds 1 credit. Large pages flattened entirely to pixels can add a compute surcharge; a free dry run quotes the exact cost. PDF/A-3b is available for the supported static document subset; Factur-X EN16931 in EUR covers controlled native invoices checked by validators. This does not certify tax compliance or accept arbitrary invoice XML. Password-protected PDF is not offered.
Who can open the files I render?
Personal live image outputs can be opened by link. Team, embedded-subject and test outputs are private and require the current authorized account or subject; document-attempt outputs also require the selected attempt. Uploaded assets are private. Every rendered file is refused after its persisted expiry, even if bytes remain in storage.
What does it cost at scale?
One-time credit packs, no subscription: $15 for 500, $35 for 2,500, up to $199 for 100,000. A finished image costs 1-3 credits by size, a preview 0.1. A standard PDF or HTML document costs 2 credits for up to 20 pages; each further started block of 20 pages adds 1 credit. Large pages flattened entirely to pixels can add a compute surcharge; a free dry run quotes the exact cost. Confirm your email to receive 50 free credits.