Changelog

Both APIs are moving to a fully EU-hosted pipeline. The current implementation routes part of the OCR and extraction work through Vertex AI and Gemini, which means non-EU processing for that step. v2 drops both and runs every step on EU infrastructure.

The pipeline is also being upgraded alongside the move, with improved accuracy across the board.

What’s changing

• Fully EU-hosted — No Vertex AI, no Gemini, no transatlantic round-trip. The DPA covers every step end-to-end.
• Higher-quality results — Upgraded extraction and OCR pipeline. Same confidence scores, more often correct.
• Same API shape — Request and response formats are unchanged. No code changes needed on your side when v2 ships.
• Same pricing — Still 1 credit per page.

We’ll post the launch date here as soon as we have one. If you’d like early access, contact us.

Send a public URL, define a schema, and get structured JSON back — using the same extraction pipeline as Document Extraction, with a new ingestor that handles web pages.

Pages are fetched with full JavaScript rendering and automatic proxy rotation so dynamic content and bot-protected sites work without any infrastructure on your end.

Send an audio file, define a schema, and get structured JSON back — using the same extraction pipeline as Document Extraction, with a new ingestor that transcribes audio.

Transcription runs on self-hosted open-weight models on EU infrastructure, so recordings never leave EU servers. Speaker detection identifies and labels each speaker automatically, and source citations include timestamps linking extracted values back to the recording.

You now get refunded for any failed request, regardless of who or what caused the failure. Previously credits were only refunded on server errors (5xx); validation failures, malformed payloads, and other client errors (4xx) consumed credits even though no work was performed on our side.

What changed

• 4xx errors are refunded — Validation failures, missing parameters, invalid base64 buffers, unknown content block types, and any other client-side error returns the credits that were reserved for the request.
• Trial credits are refunded too — Previously the refund path skipped trial grants. Trial users evaluating the platform are no longer penalized for an off-by-one in their first curl.

Why

Credits should reflect work performed, not requests attempted. A request we never executed shouldn’t draw down your balance — even if your payload was the reason we never executed it.

You don’t need to do anything. Refunds happen automatically the moment the response is returned.

Document Extraction and Document to Markdown now accept over 40 file formats — up from the original set of PDF, DOCX, XLSX, CSV, TXT, HTML, PNG, JPEG, GIF, and WebP.

New document formats:

• PPTX — PowerPoint slides extracted as markdown with formatting, bullet lists, numbered lists, and tables
• ODT — OpenDocument Text with full rich text support: bold, italic, strikethrough, links, footnotes, nested lists, and tables
• ODS — OpenDocument Spreadsheet with multi-sheet support
• EPUB — Ebook chapters converted to markdown via the HTML pipeline
• RTF — Rich Text Format with bold, italic, strikethrough, Unicode, and special characters

Email formats with attachment extraction:

• EML — Standard email format with header extraction, body parsing (plain text, HTML, multipart MIME), and automatic attachment extraction
• MSG — Outlook email format (OLE2/CFB binary) with the same header, body, and attachment extraction

Email attachments are automatically ingested through the same pipeline. A PDF attached to an email gets the same OCR and layout analysis as a standalone PDF upload. Attachments are returned separately in the response and included in the extraction context for Document Extraction. Each attachment counts as its own document for billing.

New structured/text formats:

• TSV — Tab-separated values, parsed into markdown tables like CSV
• Jupyter Notebook (.ipynb) — Code and markdown cells extracted with outputs
• LaTeX (.tex, .latex) — Converted to markdown: headings, formatting, lists, tables, math equations, links, and code blocks
• XML, YAML, TOML, RST, Org, Djot, MDX, BibTeX, Typst — Text and markup formats passed through for LLM consumption

New image formats:

• BMP, TIFF — Common raster formats
• JPEG 2000 (.jp2, .jpx, .jpm, .mj2) — Used in archival and medical imaging
• Netpbm (.pnm, .pbm, .pgm, .ppm) — Unix-origin portable image formats

All new formats work with the REST API, SDKs, and the MCP server tools (convert_document_to_markdown and extract_document).

Agencies building document and image processing pipelines for multiple clients can now apply to the partner program.

What partners get

• Dedicated support channel for technical questions and feature requests
• Early access to new APIs and features before general availability
• Volume discounts that scale with the number of active client projects
• Co-marketing through our partner directory and case study co-creation

Apply now.

Share your referral link with other developers and teams. When someone signs up through your link and makes their first API call, you both receive 500 credits.

How it works

1. Visit the new Referrals page in your dashboard to find your unique referral link.
2. Share it with anyone who could benefit from document and image processing APIs.
3. When they sign up and make their first API call, both accounts receive 500 credits automatically.

Details

• No cap on referrals — refer as many people as you want.
• Referral credits never expire.
• Credits are granted on first API call, not just signup, to prevent abuse.
• Track your referrals and earned credits from the Referrals page.

See the Referral Program docs for full details.

You can now use Iteration Layer without a monthly subscription. Pay As You Go lets you use any API and get billed at the end of each month based on actual usage.

What’s new

• No monthly commitment — use what you need, cancel anytime
• Volume discounts — per-credit rate decreases automatically as usage grows, from $0.033 to $0.022 per credit
• Trial credits included — same free trial credits as subscription plans
• Project budget caps — enforced per project, same as subscriptions
• Interactive pricing builder — estimate your cost by API on the pricing page
• Auto overage for subscribers — enable auto overage to seamlessly bill excess usage via pay-as-you-go rates when your plan credits run out
• Document Extraction and Document to Markdown now charge 1 credit per page — no more 5-credit minimum. A single-page document costs 1 credit instead of 5.

How Pay As You Go works

1. Sign up and add a card from the billing dashboard
2. Use any API — usage is tracked automatically
3. At the end of each billing period, you’re invoiced based on graduated pricing tiers
4. The more you use, the lower your per-credit rate

Subscriptions remain available for predictable monthly costs. At lower volumes, subscriptions offer better per-credit rates. Subscribers can enable auto overage for seamless overflow billing.

We updated our Terms of Service, Data Processing Agreement, and Privacy Policy to reflect how the platform works today.

What changed:

• Pay-as-you-go pricing is now covered alongside subscription plans.
• Price increase protection — if we raise prices by more than 10%, you have 30 days to cancel without further charges.
• Budget caps and overage controls are documented for subscription plans.
• Force majeure clause — obligations are suspended during events beyond either party’s control. Either side can terminate after 30 consecutive days.
• Faster data deletion — account data is now deleted within 30 days of termination (previously 90), except billing records retained for tax compliance.
• Refund policy is now cross-referenced from the Terms of Service.

What hasn’t changed: all infrastructure remains EU-hosted, sub-processors are the same, and your data is handled exactly as before.

You can now organize your API keys and usage by project. Create projects in the dashboard, assign API keys to them, and track usage per project with new filters on the Usage page.

Each project can have its own budget cap, limiting credit consumption across all API keys in that project. This replaces the previous per-key budget cap, giving you control at the level that matters — per client, per environment, or per team.

The Usage page now supports filtering by both project and product, so you can see exactly where credits are going. Projects link directly to their filtered usage view.

Budget caps move from API keys to projects. Existing API keys without a project continue to work without budget enforcement.

Build automated workflows with Iteration Layer and n8n — the open-source workflow automation platform.

Install the n8n-nodes-iterationlayer community node to get dedicated Iteration Layer resources inside n8n. Extract data from documents, transform images, generate graphics, and produce documents as part of larger automation pipelines. Self-host n8n or use n8n Cloud — both work out of the box.

See the n8n integration guide for setup instructions.

We launched a new API that exposes the first half of the Document Extraction pipeline as a standalone endpoint. Send a PDF, image, or office document — get clean markdown back.

The same OCR and layout analysis that powers Document Extraction, without the schema-based field extraction step. Tables come out as markdown tables. Headings stay headings. Scanned pages are OCR’d automatically.

For image files, the response includes a description field — a natural language description of the visual content, not just OCR text. Useful as alt text, for search indexing, or as context in LLM prompts.

Supports 40+ file formats including PDF, DOCX, PPTX, ODT, ODS, XLSX, EPUB, LaTeX, EML, Jupyter, images, and text/markup formats. Available via the REST API, all SDKs, and as a convert_document_to_markdown tool on the MCP server.

Document Generation now supports 9 font weights (thin, extralight, light, regular, medium, semibold, bold, extrabold, black) via the new font_weight field, replacing the previous is_bold boolean. PDF and EPUB render all weights as CSS numeric values (100–900). DOCX and PPTX map semibold and above to bold.

Styles and page settings are now optional. When omitted, sensible defaults are applied: PlusJakartaSans body text, Outfit headings, A4 page with 72pt margins. Only the fonts your document references are loaded, keeping output size minimal.

The Image Generation layout layer now supports background_layers, letting you place solid colors, gradients, or images behind your layout content without affecting the layer stack.

Iteration Layer is live — a unified API platform for content processing, built so developers never have to stitch together single-purpose services again.

We are launching with five production-ready APIs:

Document Extraction — AI-powered data extraction that turns PDFs, images, and office documents into structured JSON. Supports multi-file merge for combining data across documents in a single request, with field-level confidence scores you can actually trust.

Image Transformation — 24 operations covering resize, crop, format conversion, and more. Includes AI-powered upscaling, smart crop with object detection, and background removal — no ML infrastructure required on your end.

Image Generation — Deterministic, pixel-perfect image creation from JSON templates. A layer-based rendering engine with support for text, images, shapes, and QR codes, backed by 98 bundled fonts. Same input, same output, every time.

Document Generation — Generate PDF, DOCX, EPUB, and PPTX documents from JSON payloads. Bring your own fonts, use built-in templates, or define layouts from scratch. Ideal for invoices, reports, certificates, and contracts at scale.

Sheet Generation — Generate CSV, Markdown, and XLSX spreadsheets from structured JSON. Supports cell formatting, currency handling, custom fonts, merged cells, formulas, and multi-sheet XLSX output — all from a single API call.

All APIs share a unified credit pool — one subscription, one balance, no per-service billing surprises. Every request is processed on EU-hosted infrastructure with full GDPR compliance and zero data retention by default.

For AI-native workflows, Iteration Layer ships with first-class MCP (Model Context Protocol) support, so tools like Claude and Cursor can call our APIs directly.