Get Ai Usage

Today's AI request counts vs the free-tier budgets (platform admins only: the counts are app-wide), including the workspace overrides' own budgets (`provider` = `<provider>@ws-<workspace id>`). Unguarded providers (e.g. a paid Anthropic key) are not listed. Workspace search overrides are listed with `kind` = `search` (their daily bucket; RO-245). `llm_calls` sums today's recorded LLM calls (every provider, guarded or not).

API key access

Needs the workspace:read scope with an API key (ro_pat_...). A signed-in session uses the caller's role.

GET/api/v1/ai/usage

Authorization

AuthorizationBearer <token>

Access token from /api/v1/auth/login, or an API key (ro_pat_..., RO-176) from /api/v1/workspaces/current/api-keys: the key implies its workspace and needs the route's scope. MCP connectors (/api/v1/mcp only) may use an OAuth access token (ro_oat_..., RO-284).

In: header

Response Body

curl -X GET "http://localhost:8000/api/v1/ai/usage"

curl -X GET "http://localhost:8000/api/v1/ai/usage"

{
  "date": "string",
  "warn_ratio": 0,
  "llm_provider": "string",
  "llm_configured": true,
  "embedding_provider": "string",
  "budgets": [
    {
      "kind": "llm",
      "provider": "string",
      "scope": "string",
      "free_tier": true,
      "requests_today": 0,
      "daily_limit": 0,
      "rpm_limit": 0,
      "used_ratio": 0,
      "warning": true,
      "exhausted": true
    }
  ],
  "llm_calls": [
    {
      "provider": "string",
      "model": "string",
      "calls": 0,
      "errors": 0,
      "input_tokens": 0,
      "output_tokens": 0,
      "cost_usd": "string"
    }
  ]
}

Authorization

Response Body

200