Point existing tools at a governed endpoint.

Point existing software at OpenAI-compatible HTTP endpoints. The same routing, budgets, and evidence apply as for every other request.

Platform capabilities

  • OpenAI-compatible endpoints
  • API keys for your active organisation. Owners and admins create keys.
  • Each key has a data-sensitivity default and a minimum provider environment. Every request evaluates the same routing matrix before inference.
  • Unified usage and activity with per-key attribution

Who it's for

  • Automation and internal tools that need reliable multi-provider inference
  • Coding agents and orchestration layers that speak OpenAI-compatible APIs
  • Existing codebases using the OpenAI SDK: change the credentials and use Steinkauz AI within minutes
  • Organizations that want one governed layer for existing tools, custom software, and an optional built-in chat

API-specific visibility

  • Per-key attribution so you know which system used inference
  • The same D×E routing matrix as every other request, plus a key default and floor you cannot lower
  • Optional header to raise sensitivity per request without a custom request body

Full activity and administrative audit details are under Governance.

Ecosystem

Built for the AI ecosystem

Agents, automation, and custom AI systems connect to Steinkauz AI for the same models, routing, and evidence as every other request.

OpenCode

Open-source coding agent in the terminal.

n8n

Workflow automation for teams and internal tools.

Hermes

Agent runtime from Nous Research.

Paperclip

Orchestrate and run teams of AI agents.

And many more

The ecosystem grows every day. If a client speaks OpenAI-compatible APIs, it can use Steinkauz AI.

Build your own

Ship OpenAI-compatible systems on Steinkauz AI using the OpenAI SDK or any HTTP client as your foundation.

Quick start

Quick start

Create an API key in the platform, then call the endpoints with any OpenAI-compatible client.

  1. Sign up and subscribe to Steinkauz Cloud, or use a Private Deployment licence.
  2. In the platform, go to Settings → API Keys and create a key.
  3. Point your client at the Steinkauz AI base URL and send a chat completion request.
# Steinkauz AI Platform API example (OpenAI-compatible HTTP API)

# List models and pick any. For this example, we're picking the first entry of the list.
MODEL=$(curl -sS "$STEINKAUZ_BASE_URL/v1/models" \
  -H "Authorization: Bearer $STEINKAUZ_API_KEY" | jq -r '.data[0].id')

# Send a chat completion
curl -sS "$STEINKAUZ_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $STEINKAUZ_API_KEY" \
  -d "{\"model\": \"$MODEL\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]}"

Build on a governed foundation

Use the same models, providers, and policies through OpenAI-compatible APIs.

Read the docs