Claix is a B2B AI agent context infrastructure API that converts PDFs, Excel/CSV, Word/text documents and images into strictly typed JSON defined by your schema—also integrable in backend systems and automation. 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, .jpeg/.jpg/.png/.webp/.heic/.heif images, and plain text/HTML/XML via a content field. 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://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, and Txt/HTML/XML→JSON €0.10 per successful request. Temporal context window: €0.05 per call (up to 5 queries, €0.01 each). 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.

Temporary Context Window · Read

Retrieve raw content from a processed document

Endpoint

GEThttps://claix.dev/window-context/{document_id}

This endpoint returns the raw content and metadata of a specific document that was previously processed by one of Claix's extraction endpoints (pdf-json, doc-json, img-json, etc.). Unlike those endpoints, which transform a file and return schema-structured data, this endpoint is read-only: it does not process anything — it simply retrieves what was stored from a prior run — the document's raw text/markdown, when it was processed, the original file name, and which schema was used.

It is intended for server-to-server integrations (backends, scripts, n8n/Zapier/Make). Do not call it from an end-user browser because it requires a secret API key.

This call is free: it is not billed and does not consume your extraction quota, exactly like GET /api/schemas.

1. Authentication

Every request must include your API key. It is a personal server credential, distinct from any user session token.

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 returning data, 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.

2. Request format

Method: GET · Body: none · Query params: none

The document_id is part of the path — not the body or query string:

GET https://claix.dev/window-context/{document_id}

Replace {document_id}with the document's real UUID.

document_id requirements:

Must be a valid UUID; otherwise the API returns 400.
Must refer to a document that exists and belongs to the account tied to your API key.
The document must not have expired (expires_at in the past).

3. How to build the call

Have your API key ready.
Have the document_id (usually returned by an extraction with window_context enabled).
Send a GET to https://claix.dev/window-context/{document_id}, replacing {document_id} with the real UUID.
Add the authentication header.
Do not send a body or query params.
Check the HTTP status: only 200 means success.

4. Request examples

Use the panel on the right for cURL, JavaScript, Node.js, Python, PHP, and n8n examples.

5. Successful response

200 OK · Content-Type: application/json

{
  "success": true,
  "document_id": "d4a1e9d2-8b1c-4f3e-9a02-8b1e9f3c7a4b",
  "file_name": "dni_cliente_ana.jpg",
  "schema_id": "b980cfe7-61ef-4a5a-9724-881c8a5541e2",
  "processed_at": "2026-08-17T13:10:00.000Z",
  "content": "..."
}

Field	Type	Description
success	boolean	Always true when HTTP is 200.
document_id	uuid	Document identifier, matching the one in the URL.
file_name	string	Original file name as uploaded during processing.
schema_id	uuid	Schema used when this document was processed.
processed_at	datetime (ISO 8601)	When the document was processed.
content	string	Raw stored text/markdown after processing. Not the schema JSON output.

6. Error codes

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

400 — document_id is missing or not a valid UUID.

401 — Authentication failed: missing, unknown, or disabled key, or suspended account.

404 — Document does not exist, belongs to another account, or has expired (same generic message for security).

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

7. Status code summary

Code	Category	Retry?
200	Success	—
400	Client error (malformed or missing document_id)	No — fix the request first
401	Authentication error	No — fix credentials first
404	Document not found, foreign, or expired	No — fix document_id first
405	Incorrect HTTP method	No — fix the method first
500	Internal server error	Yes, with caution

8. Best practices

Always use the public domain claix.dev, not the direct Supabase URL.
Store the document_id returned by extractions if you may need raw content later — there is no document listing endpoint yet.
This call is not billed and does not consume extraction quota; use it to re-read content, cache locally, or sync your own systems.
Remember expiration (expires_at): if you need content long term, keep your own copy of content.
Never put your API key in frontend code or public repos.