Models

The models endpoint follows the OpenAI Models API  response shape. For field definitions and general behavior, refer to the OpenAI documentation.

List models

GET /v1/models

Returns an OpenAI-compatible list object:

{
  "object": "list",
  "data": [
    {
      "id": "steinkauz-gateway/openai/gpt-5.5",
      "object": "model",
      "created": 0,
      "owned_by": "steinkauz-gateway"
    }
  ]
}

Model ID format

Model IDs use the form:

{provider-slug}/{model-id}

Examples:

• steinkauz-gateway/openai/gpt-5.5 — model via Steinkauz AI Gateway
• my-azure/openai/gpt-5.5 — model on a BYOK provider you named my-azure

The provider slug matches the display name of an enabled inference provider in your account (normalized to a URL-safe slug). Use GET /v1/models to see the exact IDs available to your key.

Filtering by security classification

Your API key carries a security classification. Models whose backing provider does not meet that classification are omitted from the list and rejected on completion requests.

Availability

If one provider is temporarily unreachable, other providers may still appear in the list. An empty data array means no models matched your configuration and key classification.

Example

curl -sS "$STEINKAUZ_BASE_URL/v1/models" \
  -H "Authorization: Bearer $STEINKAUZ_API_KEY" | jq .