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.
API keys and usage belong to your active context. Create keys in Settings → API Keys while Personal or the organization you want to integrate with is selected in the organization switcher.
Supported endpoints
| Endpoint | Method | Purpose |
|---|---|---|
/v1/models | GET | List models available to your context 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 active context plan:
Gateway plans
- Individual (Personal): API requests share your System Gateway Budgets with web chat.
- Organization: API usage follows the same Budgets rules as chat for the Budget subject (member or dedicated key). Org Gateway money comes from the System Gateway pool admins allocate in Settings → Budgets—not independent non-pooled seat grants.
When Remaining reaches zero for a configured Budget unit, completions return 402 with insufficient_quota on the next gated attempt. See Usage Budgets, Gateway plans, Organization plans, and Usage, costs, and activity details.
BYOK plans
Steinkauz does not charge per inference request on BYOK plans. You pay upstream providers directly. BYOK stays uncapped by Steinkauz until you set optional Budgets. A billable seat is still required to use API Access in an organization. Usage is recorded in Usage & Activity with API key attribution.
Rate limits
Rate limits and concurrent streaming caps apply per active context. See Errors & limits.
Provider environment floor
Each API key has a Provider environment floor. Models are only available when your enabled providers meet that minimum execution environment. Unlike web chat, API keys do not evaluate the full D×E routing matrix — only the E-class floor.
Who can create API keys
In organizations, owners and admins can create and revoke API keys. Members use chat but cannot manage keys. In Personal context, you manage your own keys. See Members, roles & invites.
Usage and activity
Successful API completions appear in Usage & Activity for the active context alongside chat activity. Filter by source (API), inspect steps, and see which API key was used.
Next steps
- Create an API key in the chat app (Settings → API Keys)
- Authentication
- Chat completions with curl and SDK examples