Inventory Models

The Model Inventory answers "which models are running in our enterprise, where, and are they allowed?" Every LLM — cloud, self-hosted or on-prem — becomes a governed, attributed record.

1. Register an approved model#

curl -X POST "https://your-company.authspoke.com/api/v1/ai/models" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{
    "name": "claude-opus-4",
    "provider": "Anthropic",
    "version": "4",
    "hostingType": "CLOUD",
    "dataResidency": "US",
    "status": "APPROVED",
    "riskLevel": "LOW",
    "monthlyCostUsd": 4200,
    "complianceTags": "SOC2"
  }'

hostingType — CLOUD, SELF_HOSTED, ON_PREM. status — APPROVED, UNAPPROVED, BLOCKED, PENDING. riskLevel — LOW, MEDIUM, HIGH.

2. Block a disallowed model#

Flag models that violate policy (e.g. data-residency rules) as BLOCKED. This emits a WARNING event and pairs naturally with a DENY policy on scopeType: MODEL.

curl -X POST "https://your-company.authspoke.com/api/v1/ai/models" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{
    "name": "deepseek-v3", "provider": "DeepSeek",
    "hostingType": "CLOUD", "dataResidency": "CN",
    "status": "BLOCKED", "riskLevel": "HIGH",
    "complianceTags": "DATA_RESIDENCY"
  }'

3. List & maintain#

curl -s "https://your-company.authspoke.com/api/v1/ai/models" -H "Authorization: Bearer $TOKEN"
curl -s -X PUT "https://your-company.authspoke.com/api/v1/ai/models/$ID" -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" -d '{ "name":"gpt-4o", "status":"APPROVED", "riskLevel":"MEDIUM" }'
curl -s -X DELETE "https://your-company.authspoke.com/api/v1/ai/models/$ID" -H "Authorization: Bearer $TOKEN"

agentsUsing and monthlyCostUsd give you an attribution + FinOps view of model consumption across the estate.

Console#

Enterprise AI → Models lists every model with provider, hosting, residency, status and risk. Blocked models are visually flagged.