Cogneris API Reference

The Cogneris API exposes the platform's document intelligence engine (classification, extraction, zero-shot field discovery, cropping and splitting) through a small, focused set of HTTP endpoints. It is the same engine that powers the playground inside the Cogneris platform — wrapped behind API-key authentication so you can call it from your own systems.

APIs da Cogneris #3: Classificar documentos e extrair dados pela API do Vision Assistir no YouTube

Complete reference

Every operation, parameter, request and response attribute and error is in the API reference, generated from the same OpenAPI contract the SDKs and the Postman collection come from.

Base URL

Pick the host for the region your tenant lives in. New tenants are created in Europe:

https://api-eu.cogneris.ai    # Europe (default)
https://api-us.cogneris.ai    # United States

All endpoints documented in this section live under that host. Every request is HTTPS-only.

Authentication

Every endpoint requires an API key issued from the Cogneris platform. The key is sent on the standard Authorization header as a Bearer token:

Authorization: Bearer <your API key>

• Production keys start with xtkt_live_; sandbox keys start with xtkt_test_. The endpoints in this section are synchronous /Document/* calls and accept only production keys — a sandbox key gets 403 with the code environment.sandbox_route_unavailable. See API Authentication.
• The platform stores only a hash of the key — the plaintext value is shown to you once, at creation time. Store it in a secrets manager.
• A key can be revoked at any time from the platform. Revoked keys return 401 Unauthorized.
• The key is bound to your tenant; no extra x-tenant header is needed.

Keys are created under Vision → Developers → API Keys. See Getting Started for the step-by-step flow.

Available Endpoints

All endpoints are POST and accept multipart/form-data request bodies.

Endpoint	Purpose
POST /Document/classifier	Classifies one or more documents into the document types registered for your tenant.
POST /Document/extraction	Extracts the structured fields from a single document.
POST /Document/zero-shot	Discovers candidate fields from a document with no prior template.
POST /Document/crop	Returns the cropped/normalized version of a document image.
POST /Document/split	Splits a long PDF into the logical sub-documents it contains.
POST /Document/facematch	Compares a selfie against the photo on one or more identity documents.

Fraud verification

Endpoint	Description
POST /api/v1/fraud-verify	Checks one document for signs it was edited, fabricated or reused; returns the verdict, the signals and every check that ran. Opt-in per tenant; 8 credits per analysis.
GET /api/v1/fraud-verify/{requestId}	Reads an analysis back, including one made during an extraction.

Inside the platform, the same results and the human review of flagged ones go through Vision endpoints that use a signed-in user's platform session, not an API key: GET /vision/agent-runs/{requestId}/fraud-assessment and the fraud review endpoints (/vision/fraud/review-queue, verdict, verdict-stats).

Limits & file rules

• Accepted file types: .pdf, .png, .jpg, .jpeg, .tiff, .tif, .bmp, .doc, .docx.
• Maximum file size: 10 MB per file on every endpoint except /Document/split, which accepts up to 500 MB.
• Rate limit: 50 requests per API key per fixed 1-minute window (HTTP 429 Too Many Requests when exceeded). The window resets on the minute rather than refilling gradually.

Response envelope

Responses are always wrapped in the standard Cogneris service envelope:

{
  "data": { /* endpoint-specific payload */ },
  "meta": {
    "httpStatusCode": 200,
    "messages": []
  },
  "hasErrors": false
}

When hasErrors is true, meta.messages contains human-readable error descriptions and data is null.