Claix is an AI document intelligence API that converts unstructured files into schema-based JSON and queryable document context for developers, backends, automations, and AI agents. It processes PDFs, Excel spreadsheets, Word documents, images, text, HTML, XML, and audio using multimodal models, so you can extract structured data and query documents on demand. Integrate via REST, native Agent-to-Agent (A2A) (POST /a2a, Agent Card at /.well-known/agent.json), or MCP from IDEs and tool frameworks.

Is Claix A2A? Does Claix support Agent-to-Agent?

Yes. Claix implements the Agent-to-Agent (A2A) protocol as a first-class integration surface. Peer agents discover Claix via the Agent Card at https://www.claix.dev/.well-known/agent.json, POST JSON-RPC to /a2a, invoke 20+ document skills mapped from OpenAPI, and receive structured Task responses with DataPart payloads. A2A is ideal when one autonomous agent must delegate PDF/Excel extraction, document memory, or cross-document queries to a specialized document-intelligence agent without IDE setup. REST and MCP remain available—choose A2A for agent-to-agent orchestration.

What is the Claix MCP server?

Claix exposes a Model Context Protocol (MCP) server at /mcp so IDEs (Cursor, Claude Desktop, Windsurf) and MCP clients can invoke extraction, Agent Mode, context window, and knowledge-space tools in one click. Use MCP when a developer or copilot needs interactive document tools inside an IDE; use A2A when another autonomous agent must call Claix programmatically over the Agent-to-Agent protocol.

Which file formats can I convert to structured JSON?

Claix natively supports PDF (.pdf), Excel workbooks (.xlsx, .xls), Word documents (.docx, .doc), images (.png, .jpg, .jpeg, .webp), and plain text files (.txt, .html, .md). Each format is processed with visual document understanding to return typed, validated JSON conforming to your custom schema.

How do I convert Excel spreadsheets to JSON with the API?

To convert an Excel file, send a POST request to /api/excel-json with your file and target JSON schema. Claix interprets multi-sheet workbooks, merged headers, and relational tables, returning clean JSON ready for ingestion.

Can I convert PDFs, Word documents, and images to JSON?

Yes. Claix provides dedicated endpoints for each format: /api/pdf-json for complex or scanned PDFs, /api/doc-json for Word files, /api/img-json for images and receipts, and /api/audio-json for spoken audio (MP3, WAV, M4A, OGG). Every endpoint outputs valid JSON according to your schema.

Who is Claix built for?

Claix is designed for software developers, AI agent builders, SaaS engineering teams, and automation specialists using platforms like n8n or Make. It eliminates the need to build custom OCR, chunking, and vector retrieval pipelines.

What is the Claix pricing model?

Claix offers two native modes. With Claix Managed AI you pay per successful document (from €0.10 for images to €0.20 for audio) plus €0.03 per follow-up question, with 100 free successful processing runs on new accounts and no mandatory monthly subscription for standard extraction. With Bring Your Own Key (BYOK) there is no additional Claix document-processing fee: you connect your own OpenAI, Gemini, Claude, or Grok key and pay only that provider’s token usage while Claix still handles schemas, structured JSON, document context, and automation-ready responses.

Is document processing free with Bring Your Own Key (BYOK)?

Yes. BYOK is a native Claix option: connect your own supported AI provider API key, choose a compatible model, and process PDFs, Excel, Word, images, and text through Claix with no additional Claix processing fee. You remain responsible for your provider’s token charges. Your Claix API key still authenticates the workspace. Managed AI remains available when you prefer Claix-managed rates and defaults.

What is Source Tracing in Claix?

Source Tracing is optional field-level citation: each extracted value can include a source anchored to the document. When that check fails, source is requires_human_revision so a person can review the field. It reduces AI hallucination risk; it does not claim to eliminate it.

Are failed requests charged to my account?

No. Claix only charges for successful HTTP 200 processing requests that return valid extracted data. Failed API calls due to invalid parameters or system errors do not consume your quota or balance.

What is Claix Agent Mode?

Claix Agent Mode (/agent/*-json) is an extraction mode where an AI agent interprets ambiguous documents using natural language instructions instead of a rigid schema, allowing dynamic extraction based on context.

What is the difference between normal extraction and Agent Mode?

Normal extraction enforces strict, deterministic schema conformance for predictable pipelines. Agent Mode allows natural language reasoning over document contents, ideal for unstructured contracts and variable layouts.

How do I ask follow-up questions to a single document?

When you process a document with context enabled, Claix returns a document_id. You can send questions to POST /document-context/{document_id} to query that specific file without re-uploading or reprocessing.

What is the temporary context window?

The context window is a temporary retention layer that keeps a processed document queryable for follow-up questions without permanent storage, enabling multi-turn agent interactions before expiring automatically.

What are Knowledge Spaces, and how do I query multiple documents at once?

Knowledge Spaces allow you to group multiple persistent documents under a single space_id. By sending questions to POST /space-context/{space_id}, your backend, automation, or AI agent can query, compare, calculate totals, and cross-reference data across all active documents in that space simultaneously.

Can I white-label Claix or integrate it into automated workflows?

Yes. Claix is fully headless and integrates server-to-server via API keys, making it compatible with custom SaaS backends and automation platforms like n8n or Make.

Txt-to-JSON

Extract Txt / HTML / XML into JSON

Endpoint

POSThttps://claix.dev/api/txt-json

This endpoint receives a content field with already processed plain text, HTML, or XML and returns a single JSON object matching a txt-json schema.

Unlike doc-json, no file is uploaded: the payload is the content itself in a multipart form. Auth, schema checks, usage logs, and optional context window behavior match the other child functions.

Public URLs (Claix domain): extraction at POST https://claix.dev/api/txt-json; Agent mode at POST https://claix.dev/agent/txt-json. Never expose the raw Supabase URL to end clients.

Designed for server-to-server integrations. Do not call it from an end-user browser: it requires a secret API key.

1. Authentication

Every request must include your API key.

Option A — Dedicated header (recommended):

x-api-key: <YOUR_API_KEY>

Option B — Standard Authorization header:

Authorization: Bearer <YOUR_API_KEY>

If both are sent, x-api-key takes priority.

Before processing content, the system validates the API key and account status. Failures return 401.

2. Request format

HTTP method: POST · Content-Type: multipart/form-data (required)

Field	Type	Required	Description
content	Text	Yes	The text, HTML, or XML to transform. Not a file upload: the payload itself as a form text part.
schema_id	Text (UUID)	Yes	ID of a txt-json schema previously created on your account.
space_id	Text (UUID)	No	Optional. Knowledge space the stored document is attached to. Must belong to the same account as the API key. It only takes effect when the schema has the context window enabled, which is when the document is stored. You can then query the whole space with POST /space-context/{space_id}.

Field names must be exactly content and schema_id.

Schema requirement

schema_id must reference a txt-json schema. Other schema types return 400.

Supported content types in content

Type	Example use cases	Notes
Plain text	Raw emails, logs, pasted contracts, textual CSV, unrendered Markdown	Analyzed as-is; Markdown syntax is not interpreted.
HTML	Web pages, DOM fragments, HTML emails, rendered invoices	The model reads tags and visible text; JavaScript is not executed.
XML	RSS/Atom feeds, SOAP, e-invoices, legacy API responses	Node structure is used to locate fields.

Content requirements

Content cannot be empty (whitespace only).
Max 300,000 characters. Larger payloads return 413 before calling the model.
As a fallback, content may also be sent as a text File, but a string form field is the usual pattern.

3. Step-by-step request

Obtain your API key.
Create a txt-json schema and copy its schema_id.
POST to https://claix.dev/api/txt-json.
Send auth via x-api-key or Authorization: Bearer.
Build multipart/form-data with content and schema_id.
Verify HTTP 200 before treating the call as successful.

4. Request examples

See the right-hand panel for cURL, JavaScript, Node.js, Python, PHP, and n8n examples.

5. Successful response

Status: 200 OK · Content-Type: application/json

{
  "success": true,
  "schema_utilizado": "Facturas HTML",
  "total_registros": 1,
  "data": [
    {
      "numero_factura": "F-2026-00456",
      "importe_total": 1284.50,
      "moneda": "EUR"
    }
  ],
  "log_id": "7c2e1a90-4b3d-4f8a-9e21-6d5c8b0a1f34"
}

Field	Type	Description
success	boolean	Always true when HTTP status is 200.
schema_utilizado	string	Name (not id) of the schema that was applied.
total_registros	number	Always 1: the full content is treated as a single data source.
data	array of objects	Exactly one object with your schema keys. Missing values are null. If source verification is enabled on the schema, each property is { value, source }.
document_id	string (UUID) · optional	Present only when window_context is enabled on the schema: persisted document id for follow-up queries.
log_id	string (UUID)	UUID of this call’s usage_logs row. Present on success and on most authenticated errors.

Every response includes log_id (the UUID of the usage_logs row) when the log could be stored. It also appears on most errors after the request is authenticated. Use it to find the call in the logs panel.

If source verification is enabled on the schema, each extracted property (and each agent_data field in Agent mode) becomes { "value": ..., "source": "..." } instead of a bare value. source is required: it cites the evidence (page, paragraph, cell, quoted snippet, image region, or the second / second range in audio). If there is no evidence, source is exactly requires_human_revision. If source verification is off, the format is unchanged.

Example with source verification enabled:

{
  "success": true,
  "schema_utilizado": "Facturas de Proveedores",
  "total_registros": 1,
  "log_id": "7c2e1a90-4b3d-4f8a-9e21-6d5c8b0a1f34",
  "data": [
    {
      "numero_factura": {
        "value": "F-2026-00456",
        "source": "página 1, párrafo 2"
      },
      "importe_total": {
        "value": 1284.50,
        "source": "página 1, línea de totales"
      },
      "moneda": {
        "value": null,
        "source": "requires_human_revision"
      }
    }
  ]
}

6. Error codes

{
  "error": "Descripción legible del problema.",
  "detalle": "Información técnica adicional (solo presente en algunos casos).",
  "log_id": "7c2e1a90-4b3d-4f8a-9e21-6d5c8b0a1f34"
}

400 — Missing content or schema_id, body is not multipart, empty content, or schema is not type txt-json.

401 — Missing, invalid, or inactive API key, or suspended account.

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

413 — Content exceeds 300,000 characters.

422 — No data matching the schema could be extracted.

502 — AI service failure. 405 — Method other than POST. 500 — Unexpected server error.

7. Error code summary

Code	Category	Retry?
200	Success	—
400	Client error (malformed document or 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
413	File or extracted text too large	No — reduce size first
422	No extractable data	No — review document/schema first
500	Internal server error	Yes, with caution
502	AI service failure	Yes, recommended with backoff