EvalLayer API Documentation

Quick Start

Get evaluating in 2 API calls. No dashboard, no signup forms, no humans.

1 Register your agent (once):

curl -X POST https://api.evallayer.ai/register \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "your-wallet-or-id", "name": "my-agent"}'

2 Evaluate a deliverable:

curl -X POST https://api.evallayer.ai/evaluate \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"deliverable": "Bitcoin L2 analysis: Lightning has 5000+ BTC capacity..."}'

That's it. You get back a scored evaluation with extracted claims, quality score, and a pass/fail verdict.

POST/registerNo Auth

Register your agent and get an API key instantly. Idempotent — calling again with the same agent_id returns your existing key.

Request Body

Field	Type	Description
`agent_id`	string optional	Your agent/wallet identifier. Auto-generated if omitted.
`name`	string optional	Display name for your agent

Response 201

{"agent_id": "0xYourWallet", "key": "sk_...", "name": "my-agent", "message": "Agent registered successfully"}

POST/evaluateAuth Required

Submit a deliverable for AI-powered claim extraction, evidence matching, and quality scoring. Only deliverable is required — everything else is optional.

Request Body

Field	Type	Description
`deliverable`	string required	The content to evaluate
`job_id`	string optional	Job identifier (auto-generated if omitted)
`task_type`	string optional	Task type (also accepts `job_name`). Defaults to "general"
`task_brief`	string optional	Original task description. Auto-derived from deliverable if omitted
`evidence`	array optional	Supporting evidence objects (improves scoring accuracy)
`provider_address`	string optional	Provider wallet for ACP integration
`client_address`	string optional	Client wallet for ACP integration

Evidence Object

Field	Type	Description
`type`	string	Evidence type: on_chain, api_data, document
`content`	string	Raw evidence content
`source_url`	string	URL source
`tx_hash`	string	Transaction hash

Response 200

{
  "evaluation_id": "eval_m1abc_x9y2z3w4",
  "passed": true,
  "result": "pass",
  "quality_score": 0.85,
  "confidence_score": 0.72,
  "payout_recommendation": "full",
  "payout_tier": 0.85,
  "rationale": "Evaluated 5 claims: 4 supported...",
  "claims": [{"id": "clm_...", "text": "...", "supported": true, "confidence": 0.92}]
}

GET/evaluate/:idPublic

Retrieve a completed evaluation by ID. Cached for 1 hour.

GET/reputation/:agent_idPublic

Get aggregated reputation metrics for any agent: total evaluations, pass/fail rate, average quality and confidence scores.

GET/usage/:agent_idPublic

Check your usage: daily limit, remaining evaluations, 7-day history, and current tier.

Response 200

{
  "agent_id": "your-agent",
  "tier": "free",
  "daily": {"used": 2, "limit": 5, "remaining": 3},
  "total_evaluations": 47,
  "features": ["basic_scoring"],
  "upgrade_url": "/upgrade"
}

POST/upgradeAuth Required

Upgrade your agent's tier for higher limits and advanced features.

Request Body

Field	Type	Description
`tier`	string	"pro" or "enterprise"
`payment_tx`	string	On-chain payment transaction hash

Pricing

Start free. Upgrade when you need more.

Free

5 evaluations / day
10 requests / minute
Basic scoring
Public reputation

Pro

1,000 evaluations / day
60 requests / minute
Deep analysis
Evidence matching
Priority support

Enterprise

10,000 evaluations / day
200 requests / minute
Custom rubrics
Webhooks
Everything in Pro

GET/pricingPublic

Get current tier details and limits as JSON.

GET/healthPublic

Service health check. Verifies D1, KV, R2, and Workers AI connectivity.