API Access overview
API Access lets you call Steinkauz inference from your own applications using OpenAI-compatible HTTP endpoints and familiar SDKs.
Steinkauz is not affiliated with OpenAI. Compatibility is limited to the endpoints documented in this section.
Supported endpoints
| Endpoint | Method | Purpose |
|---|---|---|
/v1/models | GET | List models available to your account and API key |
/v1/chat/completions | POST | Chat completions (streaming and non-streaming) |
Other OpenAI endpoints (embeddings, images, assistants, and so on) are not available through API Access.
Base URL
Use your Steinkauz chat app origin as the API base:
https://chat.steinkauz.ai/v1Authentication
All requests require a Steinkauz API key in the Authorization header. See Authentication.
Billing & limits
How usage is billed depends on your plan:
Gateway plans
API requests use the same monthly inference budget as the web chat. Usage in the UI and via API draws from one shared pool. When your budget is exhausted, completions return 402 with insufficient_quota until the budget renews or you upgrade your plan. See Gateway plans and Usage statistics.
BYOK plans
Steinkauz does not charge per inference request on BYOK plans, whether you use the chat UI or API Access. You pay your upstream providers directly according to their pricing. API usage is still recorded in Settings → Usage for your reference. Provider-side quotas and billing on your own accounts still apply.
Rate limits
Rate limits and concurrent streaming caps apply per account. See Errors & limits.
Security classification
Each API key has a security classification. Models are only available when your enabled providers meet that classification.
Next steps
- Create an API key in the chat app (Settings → API Keys)
- Authentication
- Chat completions with curl and SDK examples