Quickstart — 5 minutes to your first analyzed result

Create a key

Sign in at /account, copy an API key, and set it as VERACITY_API_KEY. New accounts include starter credit for production-like smoke tests.

Send one unified request

curl https://api.veracityapi.com/v1/analyze \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"text","content":"Paste article, review, caption, or source text here...","auto_revise":true,"context":{"format":"article","intended_use":"publish"},"store_content":false}'

Use the same endpoint for type:"text" or type:"image". Text can set auto_revise:true to receive revised_text when the action is revise.

Route on recommended_action

• allow → publish or proceed
• revise → fix the flagged signals
• human_review → route to a human
• reject → block or discard

recommended_action is the primary integration field. Scores explain the route; your workflow should branch on the action.

Inspect evidence and fixes

Evidence spans and recommended_fixes tell a writer, generator, moderator, or source-checking agent what to change next. Keep store_content:false when you do not want raw submitted text retained.

Routing snippet

switch (result.recommended_action) {
  case "allow": publish(); break;
  case "revise": rewriteWith(result.evidence, result.recommended_fixes); break;
  case "human_review": queueForReview(result); break;
  case "reject": quarantine(result); break;
}

Batch + balance

POST https://api.veracityapi.com/v1/analyze-batch
GET https://api.veracityapi.com/v1/balance

Batch supports 1-25 text items. Balance returns account credit and recent usage so agents can check spend before large jobs.

TypeScript SDK

npm install @veracityapi/sdk

import { VeracityAPI } from "@veracityapi/sdk";

const client = new VeracityAPI({ apiKey: process.env.VERACITY_API_KEY });
const result = await client.analyzeText({
  type: "text",
  content: draft,
  auto_revise: true,
  context: { format: "article", intended_use: "publish" }
});

Python SDK

pip install veracityapi

from veracityapi import VeracityAPI

client = VeracityAPI()
result = client.analyze_text(
    text,
    auto_revise=True,
    context={"format": "article", "intended_use": "publish"},
)

Image curl

curl https://api.veracityapi.com/v1/analyze -H "Authorization: Bearer API_KEY" -H "Content-Type: application/json" -d '{"type":"image","content":"https://example.com/image.jpg","context":{"format":"social_post","intended_use":"moderate"},"store_content":false}'

Send HTTPS image URLs only. Returns synthetic_image_risk, evidence spans for geometry/text/lighting, and a workflow-ready recommended_action. Cost: $0.02 per image.