Categories › Business & Finance › Market data, stocks & crypto
AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
Remote server: your requests and data go to infercpi.com. Claude Code: claude mcp add --transport http infercpi https://infercpi.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
index_latest — Latest value of every index series (list-price chained/composition/hedonic, usage-weighted paid price, Törnqvist, OpenRouter shares, TPI repindex_series — Full weekly history of one series as [[unix_ts, value], ...] plus its method string. signal: price_index | weighted_index | or_rankings | imindex_catalogue — Every series the index publishes: signal/key, point count, first and last date, method string.basket — Every model priced in this week's list-price index: provider, blended $/1M (0.75 in + 0.25 out), Epoch capability score where matched.events — Priced events in first-party price lists, newest first: launch, price_cut, price_increase, removed, each with key, provider, old/new blendedspeed — Latest daily speed run, measured by the index: per model and route (openrouter default routing, openrouter_pinned to the first-party host, amodel_price — Blended list $/1M for one model by any common name ('Claude Opus 5.5', 'anthropic/claude-opus-5.5', 'gpt-5.5'); matches by the index's name open_vs_closed — Cheapest blended $/1M at each capability level (Epoch ECI 130/145/160) for closed models, open models at their lab's price and open models aself_hosting — What it costs per 1M tokens to leave the APIs: desk boxes (Mac Studio lease, RTX 5090 bought) at full and 25% duty, H100 rented by source (Vcost_per_task — Monthly measurement: dollars and tokens per completed task for the most-used models (fixed 8-task suite via OpenRouter at default settings, Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.