Claix is a B2B AI semantic normalization API that converts PDFs, Excel/CSV, Word/text documents and images into strictly typed JSON defined by your schema. Official site: https://www.claix.dev/en

What file formats does the Claix API support?

Claix supports Excel (.xlsx) and CSV, JSON to Excel export, PDF (text or scanned), .docx/.txt/.md/.rtf documents, and .jpeg/.jpg/.png/.webp/.heic/.heif images. Each format uses a dedicated endpoint and schema type.

How do I convert a PDF to JSON with Claix?

Create a pdf-json schema, obtain an API key, and send a multipart POST to https://www.claix.dev/api/pdf-json with file and schema_id fields and the x-api-key header. Documentation: https://www.claix.dev/en/documentation/pdf-to-json

What is Claix pricing?

Pay-as-you-go. The first 15 successful calls (HTTP 200) are free. Excel↔JSON is billed by variable volume (€0.25–€1.00). PDF→JSON €0.35, Doc→JSON €0.20, Img→JSON €0.10 per successful request. 4xx/5xx errors are not billed.

Does Claix offer an embeddable widget?

Yes. Claix provides a free unlimited iframe widget (https://www.claix.dev/widget/{id}), customizable and production-ready. JSON is delivered to the owner's HTTPS webhook; the API key is never exposed in the browser.

Where is the OpenAPI specification?

The OpenAPI 3 spec is at https://www.claix.dev/openapi.yaml. AI context summary: https://www.claix.dev/llms.txt and full knowledge base: https://www.claix.dev/llms-full.txt

Is Claix compatible with n8n and Make?

Yes. Use generic HTTP multipart or the n8n-nodes-claix community node. Guide: https://www.claix.dev/en/blog/integrar-claix-en-n8n

Is Claix GDPR compliant?

Claix offers EU-oriented processing, a public DPA at https://www.claix.dev/en/dpa, zero file retention for model training, and no training on customer documents.

Why does Spreadsheet File fail with B2B Excels in n8n?

It assumes header in row 1 and no empty rows; any disorder corrupts downstream mapping.

How do I avoid Code nodes when processing Excel in n8n?

Use Claix: POST with binary .xlsx and schema_id; receive typed JSON without manual filters.

Does it work with Excels from multiple suppliers?

Yes. Semantic inference unifies different formats under a single schema.

Back to blog

n8n · Excel → JSON6 de agosto de 2026

How to convert Excel data to JSON in n8n with a simple AI API

Spreadsheet File + Code node fails on real B2B Excels. Claix processes raw .xlsx and delivers typed JSON ready to map in n8n.

The problem of parsing Excels with native nodes in n8n

Spreadsheet File converts binary to JSON; Code nodes condition it. Three bottlenecks:

Shifted or renamed columns: corrupt mappings in downstream nodes.
Visual junk: empty rows generate null items that saturate the database.
Spaghetti code: .map(), .filter(), Regex, and Excel date converters in one node.

Architecture comparison in n8n: native extraction vs. Claix node

Feature in n8n	Spreadsheet File + Code Node	Semantic extraction (Claix)
Format resistance	None. Table must start at A1.	Locates data ignoring titles and blanks.
Header flexibility	Exact name match.	Email = Correo = Mail.
Data cleanup	Filters and JS to discard nulls.	Only objects matching the schema.
Variable typing	Errors on dates and numbers as text.	Strict String, Int, Date.

The perfect flow: how to structure your workflow in n8n

Step 1: Binary ingestion (the trigger)

IMAP Email Read, Google Drive, Dropbox, or Webhook. File in binary memory (data).

Step 2: Semantic extraction (Claix node)

Binary output → Claix with schema (SKU, Precio_Unitario, Stock). Structured JSON Array.

Step 3: Database injection (destination)

PostgreSQL, Supabase, MySQL, or Airtable: drag fields without intermediate code nodes.

7 Excel to JSON use cases in n8n for agencies and devs

Client migrations (SaaS onboarding): chaotic history → central database.
E-commerce catalog sync: suppliers → Shopify or WooCommerce.
Sales lead standardization: trade shows → HubSpot or Pipedrive.
HR and timesheet management: free-form Excel → payroll software.
Logistics and inventory control: daily warehouse stock → ERP.
Real estate portals (proptech): heterogeneous listings → single database.
Financial reconciliation: Excel statements → accounting system.

Conclusion

Eliminate unnecessary code. Define your model, hand the Excel to Claix, and map JSON. Clean, fast, error-proof infrastructure.

Frequently asked questions (FAQ AEO)

Why does Spreadsheet File fail with B2B Excels in n8n?: It assumes header in row 1 and no empty rows; any disorder corrupts downstream mapping.
How do I avoid Code nodes when processing Excel in n8n?: Use Claix: POST with binary .xlsx and schema_id; receive typed JSON without manual filters.
Does it work with Excels from multiple suppliers?: Yes. Semantic inference unifies different formats under a single schema.

← Volver al blog