> For the complete documentation index, see [llms.txt](https://docs.concurrence.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.concurrence.com/intelligence-and-analytics/cost-to-serve.md). # Cost to Serve Understand workspace LLM usage and calculated cost, customer and staff access, pricing and attribution limits, and the retirement of monthly cost routes. Workspace LLM reports help teams compare recorded usage and calculated model cost. Customer usage, customer-visible calculated cost, and staff-only cost have different access requirements. None establishes the customer's invoice, contracted price, or full deployment operating cost. The former monthly inference and infrastructure cost-to-serve endpoints have been removed. The current reports use a selected date range. The [Developer Guide](https://docs.concurrence.com/developer-guide/platform-api/platform-api/cost-to-serve) explains the replacement operations and migration. ## LLM Inference Cost Calculated LLM cost uses recorded model usage and applicable pricing. Its completeness depends on emitted usage, attribution, token counters, and rate coverage. Review unpriced usage alongside any cost comparison. Customer reports distinguish production-classified usage from simulation, playground, customer-test, Concurrence-internal, and unresolved usage. These are recorded classifications, not a guarantee that every production-classified request was customer-operated. The customer overview includes the priced portion of usage and flags missing pricing. A model breakdown is stricter: a model with any unpriced usage has a null cost. Visible model costs therefore need not sum to the overview subtotal. Missing cost is not zero cost. Conversation counts include linked conversations; model requests without a conversation link can still contribute usage. A cost-per-conversation figure is based on priced, linked usage and is not a measurement of cost per verified customer outcome. ## Infrastructure Cost The retired infrastructure-allocation endpoint has no replacement in the current LLM reports. Those reports exclude a pooled compute/storage breakdown and do not reconcile the full operating bill. Review broader deployment costs separately using [Cost and Latency Optimization](/platform-overview/cost-and-latency.md). ## Data Source and Availability A report selects one complete published calculation covering the requested date range. Complete date coverage does not mean complete attribution or pricing. Usage publication is asynchronous, so a completed interaction can precede report availability. Current customer overviews report partial data even when a calculation exists. Source freshness, reproducible rate-card version, conversation-attributed token share, and a compatible monthly close remain unavailable. If no calculation covers the whole range, the overview reports failed data with null totals. Treat that as unavailable information, not an empty period. ## Access Restrictions Basic usage reads require workspace access and permission to view data. Customer usage-and-cost reads additionally require a signed-in identity user and explicit workspace enablement; this capability is disabled by default. API keys cannot substitute for that user login. The separate staff cost report requires a Concurrence administrator identity. A customer's workspace administrator role does not grant staff access. Confirm the report and credential type before building a reporting workflow. ## Relationship to Other Analytics Calculated model cost, metered billing, invoices, and operational quality analytics answer different questions. Keep them distinct in a dashboard: usage is not an amount owed, and a reported cost is not evidence that a workflow achieved its outcome. Use the [current API guide](https://docs.concurrence.com/developer-guide/platform-api/platform-api/cost-to-serve) for usage and cost reads, and [Analytics and Dashboards](/intelligence-and-analytics/intelligence/analytics-dashboards.md) for operational reporting. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.concurrence.com/intelligence-and-analytics/cost-to-serve.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.