LLM spend summary
Subscription-vs-API cost split for a time range, using configured seat pricing. Accepts only seat-coherent filters: provider, user, and group scope both the usage legs and the priced seats; a model can't scope a seat, so there is no model param (and no auth_mode — the endpoint decomposes by auth path itself).
Subscription-vs-API cost split for a time range, using configured seat pricing. Accepts only seat-coherent filters: provider, user, and group scope both the usage legs and the priced seats; a model can't scope a seat, so there is no model param (and no auth_mode — the endpoint decomposes by auth path itself).
ApiKeyAuthAuthorizationBearer <token>Bearer token authentication. Send an API key (a saai_api_-prefixed token) as Authorization: Bearer <token>.
Required permission
view_llm_analyticsstart_time*stringdate-timeend_time*stringdate-timeprovider?array<>user_id?array<>user_group?array<string>The request has succeeded.
application/json- response
Subscription-vs-API cost split for a time range, using configured seat pricing.
api_equivalent*numberList-price value of all usage in range (estimate).
doubleapi_spend*numberAPI-equivalent of auth_mode=api usage — real, metered spend.
doublesubscription_spend*numberConfigured seat price × active subscription seats per calendar month touched by the range. Configured, not invoiced.
doublesubscription_savings*numberAPI-equivalent of user-attributed subscription usage minus subscription spend.
doubleseat_pricing_configured*booleanFalse until the org has any seat pricing configured; spend/savings are 0 then.
curl -X GET "https://example.com/analytics/llm-spend-summary?start_time=2019-08-24T14%3A15%3A22Z&end_time=2019-08-24T14%3A15%3A22Z"{ "api_equivalent": 0.1, "api_spend": 0.1, "subscription_spend": 0.1, "subscription_savings": 0.1, "seat_pricing_configured": true}LLM spend by group and model GET
Even-split API-equivalent spend per group × model — an estimate, not billed spend.
LLM token economics GET
Cache-hit rate, blended $/MTok, and token-type cost shares for a time range. The blended rate uses provider-reported cost. Providers don't report cost per token type, so by_type is priced from configured list prices instead and carries priced_tokens — the share of its tokens that pricing covered. For the users driving that cost, page /analytics/llm-top-users-by-cost.