Data Sources
This calculator uses a combination of official pricing, published benchmarks, and modeled reference assumptions. Each source is tagged with its provenance class throughout the product.
API Pricing
Anthropic
Model pricing from anthropic.com/pricing. Cached as of 2026-03-11. Provenance: Official
OpenAI
Model pricing from openai.com/api/pricing. Cached as of 2026-03-11. Provenance: Official
Throughput Benchmarks
InferenceX (SemiAnalysis)
Benchmark cards are normalized from the InferenceX public benchmark program. Run conditions: Rubin NVL72 hardware, FP8 precision, varying input/output lengths and concurrency. Provenance: Benchmark
Infrastructure Assumptions
NVIDIA Rubin NVL72 Architecture
Component composition (GPUs, CPUs, NICs, DPUs, NVLink fabric) from public NVIDIA materials. Provenance: Official
Beyond-rack infrastructure multipliers
Networking (15%), storage/context-memory (12%), facilities/cooling (10%), software/ops (8%) are reference assumptions derived from typical enterprise DGX SuperPOD deployments. These are NOT official NVIDIA BOMs and require real vendor quotes for procurement decisions. Provenance: Modeled
Rack lease rates
Default $45,000/rack/month is a reference estimate. Actual quotes vary significantly by term, geography, and commitment size. Provenance: Quote-driven
Power pricing
Default 7.5 cents/kWh derived from EIA industrial electricity averages. Provenance: Modeled
Data freshness: Seed data last updated 2026-03-11. Live connectors are optional and not required for the demo path. Contact Swarm Systems for current quotes and updated benchmark data.