API Access overview
API Access lets you call Steinkauz AI from your own applications using OpenAI-compatible HTTP endpoints and familiar SDKs. Chat and the API are adapters on the same organization tenant, not a separate product.
Steinkauz AI is not affiliated with OpenAI. Compatibility is limited to the endpoints documented in this section.
API keys and usage belong to your active organization. Create keys in Settings → API Keys while the organization you want to integrate with is selected.
The API authenticates the key, applies optional Budgets, and evaluates the same D×E routing matrix as chat. A usage-attempt begin row is committed before the provider call, including streams. Client-defined tools are recorded after the fact; Steinkauz AI does not execute or police them. Hash-chain or WORM tamper-evidence is not part of the product.
Supported endpoints
| Endpoint | Method | Purpose |
|---|---|---|
/v1/models | GET | List models available to your context and API key |
/v1/models/{model} | GET | Retrieve one listed model |
/v1/chat/completions | POST | Chat completions (streaming and non-streaming) |
/v1/responses | POST | Responses API core (streaming and non-streaming) |
/v1/embeddings | POST | Create embeddings on embedding-capable providers |
These endpoints implement the commonly used interoperable subset, not every OpenAI product API. Hosted state such as stored Responses, Assistants, Files, Batches, and image-generation endpoints is not available through API Access.
Base URL
Use your Steinkauz AI platform origin as the API base:
https://platform.steinkauz.ai/v1Authentication
All requests require a Steinkauz AI API key in the Authorization header. See Authentication.
Billing & limits
Steinkauz AI does not charge per inference request. You pay upstream providers directly. BYOK stays uncapped by Steinkauz AI until you set optional Budgets. Usage is recorded in Usage & Activity with API key attribution.
Optional BYOK Budgets remain. There is no included inference credit.
When Remaining reaches zero for a configured Budget unit, inference requests return 402 with insufficient_quota on the next gated attempt. See Usage Budgets and Usage, costs, and activity details.
Rate limits
Rate limits and concurrent streaming caps apply per active organization. See Errors & limits.
API routing policy
Each API key has an API routing policy: an E-class floor plus a D-class default and floor. Inference uses the same D×E matrix as web chat. Models are only listed when the enabled provider meets the E-floor and can route the key’s default data class.
Who can create API keys
In organizations, owners and admins can create and revoke API keys. Members use chat but cannot manage keys. See Members, roles & invites.
Usage and activity
Successful API completions appear in Usage & Activity for the active organization alongside chat activity. Filter by source (API), inspect steps, and see which API key was used.
Next steps
- Create an API key in the platform app (Settings → API Keys)
- Authentication
- Chat completions, Responses, and Embeddings