💰 AI Model Cost & Speed Matrix
💰 AI Model Cost & Speed Matrix
Launcher for the standalone AI: compare models on cost per request, per day and per period with prompt-caching discounts, tokens/sec and modelled latency. Your numbers, nothing fetched.
Enter your own prices and volumes and the standalone AI builds the matrix: cost per request and per period with cache hits discounted, modelled latency from TTFT and tokens per second, and which row is cheapest or fastest.
Open in the standalone AIOpens at: Dev tools → cost & latency matrix · runs entirely in your browser · no account, no API key, nothing uploaded
What the standalone AI gives you for this
- Prompt-caching savings computed over the whole period
- On-device rows cost $0 in fees but pay in seconds — shown side by side
- Nothing is fetched, so the numbers can never go stale silently
The interactive tool that used to live on this card now runs inside the standalone AI at ai.html, where it shares your indexed documents, stored memories and every reasoning method. This card stays in the catalogue as a launcher so existing links keep working.