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 do Make's native Excel modules fail?

Because they require fixed structure: exact headers, no empty rows or shifted columns.

How do I process Excels with different formats in one scenario?

With Claix: one schema defines output and semantic inference adapts each format.

Do I need routers per client in Make?

Not with semantic extraction: a single Claix node processes hundreds of distinct layouts.

Back to blog

Make · Excel → JSON6 de agosto de 2026

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

Make's native modules assume perfect tables. Claix ingests chaotic .xlsx files and returns typed JSON in three nodes without per-client routers.

The problem of parsing Excels with Make's native modules

Parse CSV, Microsoft Excel, or Google Sheets require strict column mapping. Three critical failures sink automations:

Shifted columns: a new column corrupts mapping with no visible error.
Empty rows and junk data: null records in CRM forcing complex filters.
Multiple formats: 10 clients = 10 scenarios or one giant Router.

Architecture comparison in Make: native nodes vs. Claix module

Feature in Make	Native nodes (Parse CSV / Excel)	Semantic extraction (Claix)
Structural tolerance	None. Fails if data doesn't start at A1.	High. Ignores logos and merged cells.
Column sensitivity	Breaks if names or order change.	Agnostic: Email = Correo_Electrónico.
Data cleanup	Filters for empty rows.	Only valid schema records.
Maintenance	One scenario per client format.	One node for hundreds of formats.

The perfect flow: how to structure your automation in Make

Step 1: Ingestion (the trigger)

Watch Files on Drive/Dropbox, Mailhook with attachment, or Webhook from your portal.

Step 2: Semantic transformation (Claix module)

Send the full binary to Claix with schema (SKU, Precio, Stock). You receive a clean JSON Array.

Step 3: Direct mapping (iterator and destination)

Make's basic Iterator → Airtable, PostgreSQL, Supabase, or HubSpot. No intermediate filters.

7 Excel to JSON use cases in Make for developers

Automatic CRM migrations (onboarding): chaotic Excels → Salesforce or Pipedrive.
E-commerce catalog sync: supplier prices → Shopify or WooCommerce.
Sales lead standardization: trade shows and events → marketing automation.
Time tracking and HR: weekly timesheets → payroll software.
Inventory and dropshipping logistics: daily warehouse stock → ERP.
Real estate management (proptech): agency listings → unified portal.
Financial reconciliation: Excel statements → transactional database.

Conclusion

Don't adapt your scenarios to client Excels. Define the model, pass the sheet to Claix, and map JSON. B2B integrations that don't break.

Frequently asked questions (FAQ AEO)

Why do Make's native Excel modules fail?: Because they require fixed structure: exact headers, no empty rows or shifted columns.
How do I process Excels with different formats in one scenario?: With Claix: one schema defines output and semantic inference adapts each format.
Do I need routers per client in Make?: Not with semantic extraction: a single Claix node processes hundreds of distinct layouts.

← Volver al blog