---
title: "Verify AI agent reasoning quality"
method: POST
path: "/v1/check"
---

# Verify AI agent reasoning quality

`POST /v1/check`

## Request

- Base URL: `https://api.thoughtproof.ai`
- URL: `https://api.thoughtproof.ai/v1/check`
- Auth: API key in header `X-API-Key`

Adversarial multi-model verification: independent evaluators examine the reasoning, a separate red-team model challenges their verdicts, and a synthesizer produces the final verdict. Returns ALLOW, BLOCK, or UNCERTAIN with confidence score and JWKS-signed attestation.

## Request body

- object
  - `claim` string, required: The decision or reasoning to verify
  - `stakeLevel` 'low' | 'medium' | 'high' | 'critical'
  - `domain` 'financial' | 'medical' | 'legal' | 'code' | 'general'
  - `speed` 'fast' | 'standard' | 'deep': Verification depth. Pricing: fast=$0.008, standard=$0.02, deep=$0.08 (Base USDC via x402)
  - `agentId` string: Optional caller/agent identifier for per-agent verification history (also accepted via X-Agent-Id header; body wins). Powers GET /v1/stats/{agentId} and /v1/trustscore/{agentId}.

## Response `200`

Verification result

- object
  - `verdict` 'ALLOW' | 'BLOCK' | 'UNCERTAIN'
  - `confidence` number
  - `objections` string[]
  - `durationMs` integer

## Other responses

- `402`: x402 payment required

---

[API](https://skmtc.dev/thoughtproof/apis/thoughtproof-reasoning-verification-api.md) · [All operations](https://skmtc.dev/thoughtproof/apis/thoughtproof-reasoning-verification-api/llms.txt) · [OpenAPI document](https://skmtc.dev/thoughtproof/apis/thoughtproof-reasoning-verification-api/revisions/53c58d95a03a?raw)