Compare request cost, caching scenarios, monthly spend, and embeddings across the included model set. Vendor prices and assumptions are listed below.
Runs entirely in your browser. Your numbers never leave the page.
Every number this tool shows, and where it comes from.
Pricing. Sourced from vendor pricing pages: Anthropic, OpenAI, Google, Together AI, DeepSeek.
Caching math. Anthropic prompt caching writes at 1.25x the base input rate and reads at 0.10x base. Cache TTL is 5 minutes by default. At hit rates below ~20%, caching costs more than it saves.
Forecast model. Compounding monthly volume growth at a constant per-request token shape. It does not model price changes, model deprecations, or capacity-tier discounts.
Embedding pricing. Public list pricing for Voyage AI, OpenAI, and Cohere embedding endpoints. The re-embed factor is your assumption about corpus churn or model upgrade frequency.
Caveats. Volume discounts, enterprise tiers, and regional pricing variance are not modeled. Latency, capability, and quality differences are not factored. Use these numbers as a planning baseline, not a final quote.
Pricing last verified 2026-05-06.
The rest of the toolkit runs in your browser too.
Open Orbit to choose a system, review its work, and track usage from one dashboard.
500 trial credits. Card required. $0 charged today.