Provides compute instance pricing information for DigitalOcean, enabling cost comparison across regions and instance categories.
Provides compute instance pricing information for OVH, enabling cost comparison across regions and instance categories.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Built by OptimNow. Ask an AI assistant what a model or an instance actually costs, and get a dated, sourced figure instead of a number the model remembers from its training data.
The server is hosted, so there is nothing to install.
https://optimtoken-mcp.optimnow.io/mcpThe path is /mcp. The server is tools only: answers come back as text in the
conversation, with the same figures as structured data.
Client | How to add it |
| |
Settings → Connectors → Add custom connector, paste the URL above | |
Settings → Connectors → Add, paste the URL | |
| Add an HTTP MCP server entry pointing at the URL |
Then just ask:
"We send 200k support tickets a month at about 1,500 input tokens each. Which model gives me the best quality per euro, and what would it cost?"
Related MCP server: TokenLens MCP Server
Model prices change weekly, and a language model's idea of them is frozen at its training cutoff. Ask one what Claude or GPT costs and you get a confident answer that was true some months ago, with no date attached and no way to tell. The same applies to cloud instance rates, which additionally vary by region in ways nobody memorises.
This server replaces recall with a lookup:
Live prices, not remembered ones. Every LLM figure comes from the OptimToken catalogue, which tracks 250+ models and refreshes daily.
Corrected prices. OptimToken keeps a committed price archive, a verified overrides table checked against vendor pricing pages, and an anomaly check that alarms on the half-price and double-price breaks upstream feeds occasionally publish. This server asks that catalogue rather than re-deriving prices itself.
Cost per request, not cost per million tokens. Price-per-token comparisons hide the thing you actually pay for. The tools apply your token shape, your cache hit rate and batch eligibility, and return a figure per request and per month.
Every answer carries its provenance. Which tier served it, and whether the prices were verified.
Tool | What it answers |
| "What is out there?" Browse and filter the catalogue on price, quality (Chatbot Arena ELO), efficiency and capabilities, with a self-hostability read from the licence. Ordered by ELO, or by efficiency, cost for a workload, or price with |
| "Just tell me which one." A ranked top 3 for one workload under your constraints (budget, minimum ELO, required capability, self-hostability), each with a per-constraint satisfied or violated breakdown as the evidence. Over-constrained queries return the nearest misses, labelled as such. A model whose maker has announced its retirement is never recommended, and the ones that would have ranked are named. |
| "How do these specific ones compare?" 2 to 4 named models across all 8 use case profiles at a chosen monthly volume, list and optimized cost for each. |
| "What will this cost us per month?" Per-request and monthly cost for your own volume, token shape, cache hit rate and batch eligibility. |
| "What should we run it on?" Compute instance rates across AWS, Azure, GCP, OCI, OVH, DigitalOcean and Alibaba, by region and category: on-demand, spot, and 1- and 3-year commitments, each with what it saves against on-demand. |
| "Where do we buy it?" For 1 to 4 named models: how many hosts sell each, the cheapest, the dearest, the model maker's own rate, promotional listings, then every host with its rate, the platforms that list the model and its Amazon Bedrock regions, and what your workload costs at each. Says when the cheap host serves a quantized build. |
| "API, or our own GPUs?" The monthly volume at which renting an instance costs the same as paying a model's API per token, at every rate the instance lists (on demand, spot, commitments) and against the API at list price, optimized, and at the cheapest host. It assumes no throughput and no staffing cost: give yours, or it states the tokens per second the break-even would require and says the figures are hardware rent only. |
All seven are read-only and take no credentials. Nothing you send is stored.
End of life is on every answer. A model whose maker has announced the retirement of its API is labelled with the date and the replacement the maker names, wherever it appears, and loses the FinOps Friendly badge. The notices are read by hand from each maker's deprecation page and dated in the response; a model with no label has no notice on record, which is not a guarantee.
Use case profiles ship with realistic token shapes, so you do not have to invent them: Support Ticket, Knowledge Q&A, Meeting Summary, Marketing Content, Coding Task, Invoice Processing, Call Summary, Agent Workflow.
optimtoken.optimnow.io is the single source of truth. When it cannot be reached, the
server degrades in tiers rather than failing, and says which tier it used.
Tool | Tier 1 | Tier 2 | Tier 3 |
LLM tools |
| OpenRouter direct | embedded snapshot |
Compute tool |
| not available | embedded snapshot (137 rows) |
Tiers 2 and 3 serve uncorrected prices, and that matters more than it sounds. An
upstream feed once published a frontier model at half its real list price, which halves
every monthly figure derived from it. So every response carries a provenance object
with pricesVerified, and the lower tiers put a notice at the top of the answer. A
fallback should never quietly downgrade correctness.
Tier 1 is accepted only when the catalogue reports that it is itself serving fresh upstream data. If the site is on its own fallback, it carries no corrections, and this server treats it accordingly.
Requires Node.js 24+.
npm install
npm run dev # the server with reload, at http://localhost:3000/mcp
npm test # cost logic, schema conformance, data sources, the HTTP layer
npm run build # tsc, to dist/server/src/index.jsThe static fallback catalogue is refreshed by hand, not on a schedule:
npm run refresh-fallbackBecause it is manual, check its dataAsOf before trusting a tier-3 response. An
unrefreshed fallback ages silently.
ai-pricing-hub-mcp/
├─ server/src/index.ts # the seven tools
├─ server/src/lib/http.ts # Streamable HTTP at /mcp, one MCP server per request
├─ server/src/lib/optimtoken-api.ts # the one base URL constant, fetch and timeout discipline
├─ server/src/lib/ # ranking, efficiency scoring, provenance, normalisation
└─ server/src/data/ # static fallback pricing + region mapsBuilt on the official MCP TypeScript SDK, with no framework and no UI layer. Deployed on Fly.io.
The web app. Same catalogue, full UI, an AI advisor and a public JSON API. | |
Does the AI business case pay for itself. Same prices, plus harness costs and value modelling. | |
FinOps knowledge for AI agents: AWS, Azure, GCP, AI inference, SaaS. | |
MCP servers, tutorials and client guides for cloud cost work. |
Released under the MIT License.
Prices served by this server come from third-party sources and are provided as is, without warranty. Verify against vendor pricing pages before committing spend.
Questions about your own AI or cloud bill? Talk to OptimNow.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Look up, compare and track AI model API prices from an AI assistant. No sign-in needed.
Find AI model pricing, estimate token costs and compare offers. No API key required.
LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
