run.pay for AI Agents

This page is optimized for AI agents and LLMs to discover and understand run.pay's services.

What is run.pay?

run.pay is a pay-per-call API marketplace for AI agents. Your agent calls a service, pays automatically via Stripe, gets the result. 205 services across AI quality, security, compliance, data processing, and reasoning.

Machine-readable resources

OpenAPI 3.1 spec — Full API documentation
llms.txt — LLM-readable site description
skill.md — Agent skill file (Claude, GPT, Gemini)
.well-known/agent.json — Agent discovery
MCP on Smithery — One-click Claude Desktop install

Quick start for agents

# 1. Get a free agent ID
curl -X POST https://runpay-backend-visibility-production.up.railway.app/playground/quick-signup \
  -H "Content-Type: application/json" \
  -d '{"email": "your@email.com"}'
# Returns: {"agent_id": "agt_xxx", "mode": "trial"}

# 2. Discover services
curl https://runpay-backend-visibility-production.up.railway.app/api/services/catalog

# 3. Call a service
curl -X POST https://runpay-backend-visibility-production.up.railway.app/x402/halludetect \
  -H "Content-Type: application/json" \
  -H "x-agent-id: agt_xxx" \
  -d '{"response": "According to Harvard, 73.2% of AI models hallucinate."}'

Python SDK

pip install runpay

import runpay
runpay.configure(agent_id="agt_xxx")
result = runpay.call("halludetect", {"response": "text to check"})
print(result["hallucination_score"])  # 87

JavaScript SDK

npm install runpay

const runpay = require('runpay')
runpay.configure('agt_xxx')
const result = await runpay.call('halludetect', { response: 'text to check' })
console.log(result.hallucination_score) // 87

Service categories

AI · 47 services Security · 38 services Compliance · 31 services Data · 52 services Reasoning · 37 services

Authentication

Header: x-agent-id: agt_your_id — Get a free ID at getrunpay.com/playground (3 free calls per service, no card needed).

Pricing

$0.001–$0.10 per call · 2% platform commission · $0 monthly fee · $0 setup