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.

Does Gemini read Excel files directly?

No. You must convert .xlsx to CSV or text in your backend before sending to the API.

Why do webhooks fail with Gemini and large Excels?

Because of 20–60 second latency that exceeds Make, n8n, or serverless function timeouts.

How do I avoid Vertex AI for processing Excels?

Use Claix: POST with raw .xlsx and schema_id, without SDKs or Google service accounts.

Back to blog

Excel → JSON6 de agosto de 2026

Why using Gemini's API to extract Excel to JSON is a production mistake (and the alternative)

Gemini forces CSV, fires junk tokens, and timeouts on webhooks. Claix ingests raw .xlsx and returns typed JSON without Google Cloud.

The mirage of the infinite context window

Gemini memorizes giant CSVs, but B2B extraction is a format and speed problem. Empty columns, merged cells, and metadata become millions of tokens the LLM processes character by character.

Architecture comparison: Gemini API vs. specialized API (Claix)

Technical feature	Generic API (Gemini 1.5 Pro)	Specialized middleware (Claix API)
File ingestion	Requires .xlsx to CSV parser on your server.	Directly ingests raw .xlsx or .csv.
Latency	Extremely high. More rows, more wait.	Agile responses for automation.
Infrastructure management	Vertex AI, IAM, GCP Service Accounts.	None. One HTTP endpoint with API key.
Timeout handling	Webhooks and Lambda fail from waiting.	Architecture that doesn't block your backend.
Type validation	Hallucinates on empty cells or breaks schema.	Guaranteed String, Int, Boolean.

The 3 technical walls when processing Excels with Gemini

1. Latency penalty and timeouts

5,000 rows mapped to JSON Schema can take 20–60 seconds. Vercel, Lambda, or Make close the connection before Google responds.

2. Junk token cost

Every comma and empty cell in CSV consumes input tokens. Daily inventories and client databases mean millions of deep learning tokens for mapping and cleanup.

3. Google Cloud bureaucracy (Vertex AI)

Real production requires Vertex AI: heavy SDKs, service accounts, IAM permissions. All that boilerplate just to pull four columns from an Excel.

The solution: dedicated data transformation API

Define SKU, Precio, and Stock in the panel, POST your .xlsx without CSV conversion, and receive clean JSON. Zero extreme latency, zero Google Cloud.

7 use cases where avoiding Gemini saves your infrastructure

CRM migrations (HubSpot/Salesforce): chaotic Excels without timeout.
E-commerce catalog sync: prices from dozens of suppliers.
No-Code Make/n8n flows: HTTP module without Google OAuth2.
Trade show lead ingestion: contacts to JSON in real time.
HR time tracking: strictly typed numeric fields.
Dropshipping logistics reports: automated daily inventories.
Financial reconciliation: massive statements without hallucinating dates.

Conclusion

Parsing B2B Excel doesn't require 2 million tokens: it requires strict typing, low latency, and simple integration. Hit our endpoint with the Excel and receive data ready for your database.

Frequently asked questions (FAQ AEO)

Does Gemini read Excel files directly?: No. You must convert .xlsx to CSV or text in your backend before sending to the API.
Why do webhooks fail with Gemini and large Excels?: Because of 20–60 second latency that exceeds Make, n8n, or serverless function timeouts.
How do I avoid Vertex AI for processing Excels?: Use Claix: POST with raw .xlsx and schema_id, without SDKs or Google service accounts.

← Volver al blog