AI Inference

Hosted models, billed on usage, called like OpenAI.

Open AI Inferencein the current project. This is a separate API from the platform HTTP API. Platform keys (nodion_…) manage resources. Inference keys (nodion_ai_…) call models.

Tabs

• Keys: create a key. It is shown once. Optional expiry and a daily spend limit. Only a project admin can create or revoke keys.
• Playground: try chat (and other modes when models exist). Playground traffic is metered like any other request.
• Models: catalog and readiness.
• Usage and Requests.
• Billing: a prepaid wallet, separate from the monthly platform invoice. Top up with card or PayPal.
• Settings: optional region allowlist, and policy toggles such as zero data retention.

Call the API

bashcurl https://api.nodion.ai/v1/chat/completions \
  -H "Authorization: Bearer $NODION_AI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "<model>", "messages": [{"role": "user", "content": "Hello"}]}'

List models withGET https://api.nodion.ai/v1/modelsor on the Models tab. Prices are there too, not on the platform price book. AI spend comes from the wallet, not from the platform invoice.

Agents that manage the cloud

To let Cursor or Claude create apps and databases, use MCPwith a personal platform key, not an inference key.