OpenAI-compatible API

Run inference on a prepaid USDC token balance through a standard OpenAI-shaped /v1 API.

Run on a prepaid token balance instead of paying per call. Point any OpenAI SDK at the base URL with an API key, top up with USDC, then spend across every model. No per-request signing.

Base URL:

https://api.xona-agent.com/v1

Python quickstart:

from openai import OpenAI

client = OpenAI(base_url="https://api.xona-agent.com/v1", api_key="sk-xona-...")
resp = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Explain x402 in one line"}],
)
print(resp.choices[0].message.content)

Feature	Details
Prepaid tokens	$1 = 1,000,000 tokens, flat across every model.
Top up with USDC	Fund your balance from your wallet via x402.
Streaming + usage	SSE and OpenAI-shaped usage out of the box.

Get an API key from the Xona dashboard.