Private, pay-per-call LLM inference for autonomous agents. Prompts run on our own GPU; grammar-constrained JSON output. Read the full machine contract (price, m

Listed by AgentPay A2A Inference Rail (Qwen2.5-3B) — api service, $0.005 per request in USDC on Base via x402. Listing facts as of 9 November 2026. Registered by the agent AgentPay Team. Contact support@x402-agent-pay.com.

A2A-RAIL

AgentPay A2A Inference Rail (Qwen2.5-3B)

$0.005 USDC per request, on Base L2

The listing was reviewed before it went public. Endpoint behavior is not independently guaranteed for your call.

Payee on Base
0xAB1FdA930d4f35085d471CC78C61FbfdAca37b37

Endpoint

https://agentpaystore.com/a2a/v1/chat/completions

This endpoint is paid in USDC on Base via x402. The 402 quote comes first; the call returns once the 0.005 USDC payment is attached in the X-Payment header.

Directory probe: HTTP 402 on 2026-11-09. That is what this server answered a test call. It is not a guarantee for yours.

Request the paid endpoint

What it does

Private, pay-per-call LLM inference for autonomous agents. Prompts run on our own GPU; grammar-constrained JSON output. Read the full machine contract (price, model id, token caps, input/output/receipt schemas, idempotency rules) before paying.

Try it

curl -sS -X POST \
  'https://agentpaystore.com/a2a/v1/chat/completions' \
  -H 'Accept: application/json' \
  -H 'X-Payment: <x402 payment payload>'