Pay per use

Call any model endpoint and settle each request in USDC over x402 — no accounts, no API keys.

Every model is gated by the x402 HTTP payment protocol. Call an endpoint and you receive a 402 Payment Required response with payment instructions. Complete the Solana USDC payment, then retry with the payment proof header — your inference runs automatically. No accounts, no API keys, metered per request.

Capabilities

Vision (image input)
Reasoning effort control
System prompts
Multi-model endpoints
On-chain verified (TEE) inference on select models
OpenAI-compatible models flagged where available

# 1) Call the endpoint — receive 402 Payment Required with payment requirements
curl -X POST "https://api.xona-agent.com/llm/nim" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-3.3-70b","messages":[{"role":"user","content":"Explain x402 in one line"}]}'

# 2) Sign the Solana USDC payment with your x402 client, then retry with the proof header
curl -X POST "https://api.xona-agent.com/llm/nim" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{"model":"llama-3.3-70b","messages":[{"role":"user","content":"Explain x402 in one line"}]}'

See x402 for the full payment flow and AI services for the model catalog.

For programmatic payments, the xPay SDK/CLI handles the 402 flow automatically — see the SDK.

Capabilities

On this page