InferCPI
Server Details
AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Infer-CPI/api
- GitHub Stars
- 0
- Server Listing
- infercpi
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
Most tools have clearly distinct purposes: basket lists all models with prices, model_price looks up a single model, index_latest/index_series handle index series, and events/cost_per_task/self_hosting/speed cover separate analytical outputs. Minor overlap exists between basket and index_latest (both return latest values) and between open_vs_closed and self_hosting (both compare costs), but descriptions clarify the boundaries well enough.
All tool names use consistent lowercase snake_case (e.g., cost_per_task, index_latest, open_vs_closed). However, the pattern is noun-based rather than the ideal verb_noun convention, and a few names are single words (basket, events, speed), making the set slightly less predictable than a uniform verb_noun scheme.
Ten tools is a well-scoped number for an AI pricing and benchmarking index. Each tool maps to a distinct published output (basket, events, index series, cost per task, self-hosting, speed), and none feel redundant or superfluous.
The surface covers core lifecycle needs: current model prices, historical index series, price events, task costs, open vs closed comparisons, self-hosting economics, and speed benchmarks. Gaps include per-model historical price series and search/filter operations (e.g., by provider or capability), though agents can mostly work around these using basket and model_price.
Available Tools
10 toolsbasketBInspect
Every model priced in this week's list-price index: provider, blended $/1M (0.75 in + 0.25 out), Epoch capability score where matched.
Inputs: no named parameters.
cost_per_taskBInspect
Monthly measurement: dollars and tokens per completed task for the most-used models (fixed 8-task suite via OpenRouter at default settings, charged cost), reasoning share of output tokens, accuracy, and medians.
Inputs: no named parameters.
eventsAInspect
Priced events in first-party price lists, newest first: launch, price_cut, price_increase, removed, each with key, provider, old/new blended $/1M and pct. since: ISO date; kind: filter to one kind.
Inputs: kind, since.
index_catalogueBInspect
Every series the index publishes: signal/key, point count, first and last date, method string.
Inputs: no named parameters.
index_latestAInspect
Latest value of every index series (list-price chained/composition/hedonic, usage-weighted paid price, Törnqvist, OpenRouter shares, TPI replica) with dates, the latest editorial note, and the licence/attribution line. Start here.
Inputs: no named parameters.
index_seriesAInspect
Full weekly history of one series as [[unix_ts, value], ...] plus its method string. signal: price_index | weighted_index | or_rankings | implied_margin | self_host | task_cost | hf_downloads | gpu_spot | gpu_neocloud | aws_gpu | speed | hyperscaler_capex | seller_revenue | cloud_revenue | token_price ... key: see index_catalogue. since: optional ISO date to cut the history.
Inputs: key (required), signal (required), since.
model_priceAInspect
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 normaliser and returns every basket entry that matches.
Inputs: name (required).
open_vs_closedBInspect
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 at the cheapest third-party host; the open discount; DeepSeek's floor lift (cheapest price without DeepSeek / cheapest overall, at lab and at host prices); and the host discount per open model (lab price / cheapest host).
Inputs: no named parameters.
self_hostingAInspect
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 (Vast, AWS, RunPod, CoreWeave, Lambda, Nebius) and owned, against the API price of the same open model and of the cheapest closed model at equal capability; break-even volume and how far hardware cost must fall. Plus posted GPU-hour prices and Hugging Face download counts.
Inputs: no named parameters.
speedAInspect
Latest daily speed run, measured by the index: per model and route (openrouter default routing, openrouter_pinned to the first-party host, anthropic and openai direct), median time to first token (ms), visible output tokens per second, host that served it. Same prompt every day.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
The global price benchmark for AI inference: 23 price indexes, market KPIs and SKU-level prices.
AI inference pricing for agents: live and historical model prices, provider comparison.
Verified, dated prices for 293 AI APIs in 45 markets: LLMs, GPUs, speech, video and more.
AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
Related MCP Servers
- AlicenseAqualityBmaintenanceLive LLM API pricing: current token prices, model comparisons, cheapest-model lookups, and The LLM Price Index for 150+ models across 20+ providers, re-verified daily. No API key required.41MIT
- AlicenseAqualityBmaintenanceGlobal price benchmarking for AI inference across 2,600+ SKUs from 47 vendors. Query live pricing, market indexes, and model specs via 8 tools. Free tier available.859 npmMIT
- AlicenseNot gradedqualityCmaintenanceToken cost math for LLM API calls: current per-million-token rates for 69 models across 17 providers, with local arithmetic for estimates, comparisons and monthly budgets. Rates are verified and date-stamped.57 npm2MIT
- AlicenseAqualityBmaintenanceLLM API prices, cost estimates, model comparisons and language token tax for GPT, Claude and Gemini.7170 PyPIMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.