Cost Planning
Pricing and model availability change. Build a workload-specific estimate from current official rates, measured session usage, integration charges, and the human work needed to review and operate the system.
Two Dimensions of Cost
Managed sessions consume model tokens. Model, cache behavior, context size, tool results, retries, and inference settings affect the bill. Read the current pricing page at estimation time.
Use the authoritative usage and list-cost fields emitted for each session.
Session runtime and any separately metered server tools contribute to cost under the current contract. Set a session max_list_cost budget and application limits before sending work.
Source: Anthropic's current pricing and session budget documentation. Contract terms, negotiated rates, taxes, cloud platform charges, and upstream APIs can differ.
Select a Model by Evaluation
Do not preserve a permanent “best model” ranking in course content. Shortlist currently supported models, then choose the least-cost option that clears your task's quality, safety, latency, and reliability gates.
| Evaluation slice | Measure | Release gate | Evidence |
|---|---|---|---|
| Representative | Accuracy, groundedness, reviewer effort | Your task-specific minimums | Versioned fixture set and human labels |
| Adversarial | Prompt injection, secret handling, unsafe tool attempts | No unauthorized action or data crossing | Attack cases plus approval-event audit |
| Regression | Quality, p95 latency, list cost, error rate | No material degradation from approved baseline | Pinned agent version and reproducible run log |
Three Cost Controls
A list-price estimate is a starting point, not a budget or a business case.
budget_reached safely3 Pilot Worksheets
These are planning templates, not measured customer results. Populate them with synthetic test runs, then repeat on an approved, minimized data sample.
- Inputsaccounts x campaigns x date range
- Measurelist cost + active time + reviewer minutes
- Quality gateschema checks + cited anomalies
- Safety gateread-only scopes + tenant isolation
- Inputsbrief size + policies + approved sources
- Measurelist cost + latency + revision time
- Quality gatepolicy, math, and claim checks
- Safety gateno spend, publish, or audience write tool
- Inputsevents/day + context/event + lookback
- Measurelist cost + precision + recall + alert load
- Quality gatefalse-positive budget + reviewed alerts
- Safety gatealert only + stop switch + rate cap
Total Cost of Ownership
Do not compare an API subtotal with a person's salary. Compare equivalent, quality-controlled operating models and include integration, review, failure, security, and compliance costs.
Measure Caching; Do Not Promise Savings
Prompt caching can change input cost, but the realized effect depends on cache-eligible content and hit rate. Compare equivalent runs and read the current pricing rules.
Keep model and Agent version, fixture set, tool policy, and inference settings constant when comparing. A lower bill is not a win if quality, safety, or reviewer effort regresses.