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.

Excel-to-JSON · Agent mode

Excel / CSV to JSON with Agent mode

Endpoint

POSThttps://www.claix.dev/agent/excel-json

Agent mode active

This endpoint runs structured extraction from the main schema first, then a reasoning phase with agent_definition. The response includes data[] (extraction) and agent_data (typed inference). The schema must have is_agent_mode enabled.

This endpoint accepts a tabular file (.xlsx or .csv) and returns it transformed into JSON with the exact structure you define via a schema. The file columns do not need to match schema property names literally: the system automatically recognizes synonyms, abbreviations, translations, and variants.

It is intended for server-to-serverintegrations (backends, scripts, n8n/Zapier/Make). It must not be called from an end user's browser because it requires a secret API key.

1. Authentication

Every request must include your API key. It is a personal server credential, distinct from any session token, and should be handled with the same care as a database password.

Option A — Dedicated header (recommended):

x-api-key: <YOUR_API_KEY>

Option B — Standard Authorization header:

Authorization: Bearer <YOUR_API_KEY>

Either one is sufficient. If you send both, x-api-key takes priority.

Before processing the file, the system validates that:

The API key exists and is active.
The associated account is active (not suspended).

If validation fails, the request is rejected with 401 without processing the file.

2. Request format

Field	Type	Required	Description
file	Binary file	Yes	Excel (.xlsx) or CSV (.csv). Must be the file itself, not a path or URL.
schema_id	Text (UUID)	Yes	Identifier of the excel-json schema created in your account.

Method: POST · Content-Type: multipart/form-data

Field names must be exactly file and schema_id. The schema must be of the Excel → JSON type; if you send one of the opposite type, you will receive 400.

File requirements:

Formats: .xlsx, .csv.
At least one header row and one data row.
If there are multiple sheets, only the first is processed.

3. How to build the request

Have your API key and the correct schema_id ready.
Build a POST request to the endpoint URL.
Add the authentication header.
Send multipart/form-data with file and schema_id.
Check the HTTP status code: only 200 indicates success.

4. Request examples

See the panel on the right for examples in cURL, JavaScript, Node.js, Python, PHP, and n8n. You can switch languages with the selector at the top and copy the code directly.

5. Successful response format

200 OK · Content-Type: application/json

{
  "success": true,
  "schema_utilizado": "Inventario Q3",
  "total_registros": 2,
  "data": [
    { "sku": "SKU-001", "stock": 120, "precio": 19.99 },
    { "sku": "SKU-002", "stock": 45, "precio": 34.5 }
  ],
  "agent_data": {
    "stock_critico": true,
    "productos_bajo_minimo": 1,
    "resumen_inventario": "Un producto por debajo del umbral mínimo de stock."
  }
}

Field	Type	Description
success	boolean	Always true when HTTP is 200.
schema_utilizado	string	Name of the schema used for extraction.
total_registros	number	Number of records in data.
data	array	Objects extracted from the main schema (same as extraction mode).
agent_data	object	Typed Agent Mode answers per agent_definition (booleans, numbers, strings).

6. Error codes

{
  "error": "Descripción legible del problema.",
  "detalle": "Información técnica adicional (solo presente en algunos casos)."
}

400 — Invalid request: missing file or schema_id, incorrect multipart, corrupt file, no data rows, or schema of the wrong type.

401 — Authentication failed: key missing, nonexistent, deactivated, or account suspended.

404 — schema_id does not exist or does not belong to your account.

422 — File read but no matches with the schema.

502 — AI service failure (transient; retry with backoff).

405 — Method other than POST. · 500 — Internal error.

7. Code summary

Code	Category	Retry?
200	Success	—
400	Client error (malformed data)	No — fix the request first
401	Authentication error	No — fix credentials first
404	Resource not found	No — fix schema_id first
405	Incorrect HTTP method	No — fix the method first
422	No matches found	No — review data/schema first
500	Internal server error	Yes, with caution
502	AI service failure	Yes, recommended with backoff

8. Best practices

Validate the HTTP status code before reading data.
Only columns with a real match in the schema appear.
Retry automatically only on 500 and 502, never on 4xx unless the request changes.
Save mapa_columnas for traceability during testing.
Do not include your API key in frontend code or public repositories.