Getting started
Quickstart
Keep the OpenAI client you already ship - swap the base URL and key, and your first call settles itself.
Chat completions
Streaming and non-streaming are both supported.
python
from openai import OpenAI
client = OpenAI(
base_url="https://api.arcencompute.com/v1",
api_key="ar_sk_live_…",
)
resp = client.chat.completions.create(
model="glm-5.2",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)List models
Returns the enabled catalog with per-token USDG pricing.
curl
curl https://api.arcencompute.com/v1/models \
-H "Authorization: Bearer ar_sk_live_…"That's it
Every call is metered at its exact token count, charged in USDG, and settled on-chain in the background - no gas, nothing recurring. Watch your spend live from the dashboard.