ComparEdge LLM Cost

io.github.imkemit-opsPublished by GitHub account imkemit-opsv1.0.0Updated Oct 25, 2026

Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.

The publisher's own server: Edge Network

VerifiedSTDIODesktop onlyFinanceAI & ML

Overview

AI-generated overview

A local MCP server that gives an assistant verified per-million-token LLM API rates for 69 models and computes call, workload and budget costs.

What you can do
Estimate the dollar cost of one call or many identical calls for a given model and token counts, including cached and batch options where offered. Compare the same call across two to six models, ranked cheapest first. Project daily, monthly and yearly spend for a workload from call volume and average token counts. Find the lowest-cost models, optionally above a context-size floor, and list tracked models and providers with rates and context.
When to use it
Useful when planning or explaining what an AI feature will cost at scale, choosing between models on price, or forecasting a monthly LLM bill, and you want figures tied to a dated price feed rather than the model's remembered prices.
Requirements
Runs locally over stdio, typically launched with npx from the npm package, so Node.js is needed. No API key or account. It fetches one public price feed over the network and caches it for about six hours, serving the last good copy if the fetch fails.
Before you install
Cost figures are estimates based on a third-party price feed and token counts you supply; they are not billing records, and actual charges may differ. The server sends no credentials and calls no provider API, but it does make a network request to fetch the public price feed.

Installation

In SourceWeft

  1. Open ComparEdge LLM Cost in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Someone asks what the AI feature will cost at scale, and the honest answer around most teams is a shrug. Rates moved twice since anyone last checked, and the model itself will happily quote prices from its training data. This MCP server keeps current per-million-token rates for 69 models where your assistant can reach them, and does the arithmetic itself.

Watch it work

$ You: price Claude Opus 4.8 on a 25k-token prompt with a 1k answer, run 5,000 times
  llm-cost › estimate_cost
  Cost estimate: Claude Opus 4.8 (Anthropic)  Rates: input $5/1M, output $25/1M, cached input $0.5/1M
  Per call (25,000 in + 1,000 out tokens):    input:  $0.1250    output: $0.0250    per call total: $0.1500
  Across 5,000 calls: $750.00
  Ways to pay less for the same 5,000 calls:    with cached input:  $187.50    via batch API:      $375.00

Nothing here is rounded or guessed. The rate is verified, date-stamped, and the server multiplied.

Open a second session: same call across four models, ranked 
$ You: compare that call on Opus 4.8, Sonnet 5, GPT-5.6 Terra and Gemini 3.1 Pro
  llm-cost › compare_models_cost
  25,000 in + 1,000 out, cheapest first:
  1. Claude Sonnet 5      $0.0600 /call    $300.00 /5k  2. Gemini 3.1 Pro       $0.0620 /call    $310.00 /5k  3. GPT-5.6 Terra        $0.0775 /call    $387.50 /5k  4. Claude Opus 4.8      $0.1500 /call    $750.00 /5k
  Ranking uses each model's live feed entry, not remembered prices.

The gap it closes

An assistant on its ownAn assistant with llm-cost
quotes output rates from training data, often a generation stalereads the current rate, dated
flattens the estimate to "a few cents"$0.1500 per call, $750.00 across 5,000
never mentions batch or caching discounts$375.00 batch, $187.50 cached, only where the model really offers them
confidently wrong, no way to tellevery figure traces to a feed entry with a verification date

The same numbers answer in a browser through the LLM calculator, and the LLM category hub ranks every tracked model by rating and price.

Where the numbers travel

mermaid
flowchart LR    V["provider pricing pages<br/>17 providers"] --> CE["verification<br/>date-stamped checks"]    CE --> F["model prices feed<br/>69 models, USD per 1M tokens"]    F -->|"6h cache, serve stale on failure"| MCP["llm-cost server<br/>local arithmetic"]    MCP --> A["your agent"]

The server never calls a provider API. It reads one public feed, llms-model-prices.json, and computes locally. Nothing to rate-limit, no key to leak, and a network hiccup serves the last good copy instead of an error. How each price gets checked is written up in the methodology, and the catalog behind it ships as an open dataset under CC BY 4.0.

The six tools

Four do the math. Two help you find the exact model id the math wants.

ToolAnswersParams
estimate_costone call, or N identical calls, in dollarsmodel, input_tokens, output_tokens, calls?
compare_models_costthe same call priced across 2 to 6 modelsmodels[], input_tokens, output_tokens
monthly_budgetdaily, monthly, yearly spend for a workloadmodel, daily_calls, avg_input_tokens, avg_output_tokens
cheapest_modelslowest-cost models, optional context floormin_context?, limit?
list_modelsevery model with rates, context and tierprovider?
list_providersproviders with model counts and cheapest picknone
Token rules of thumb, for when nobody knows the counts
  • A page of English prose is roughly 500 tokens; one token is about four characters.
  • Model references are forgiving: claude-opus-4-8, Opus 4.8 and anthropic/opus resolve to the same model. When the resolver is unsure, it returns candidates instead of guessing.
  • cheapest_models ranks by a blended rate weighting input to output 3 to 1, because real workloads read far more than they write. Confirm the winner with estimate_cost on your actual split.

Prompts

PromptArgsRuns
estimate_my_workflowworkflow, model?token estimates plus per-run and monthly cost for a described workflow
pick_cheapest_modeltaskcheapest model that still meets the requirement, top candidates priced
forecast_ai_budgetmodel, usagemonthly and yearly bill projected from expected volume

Wire it up

json
{  "mcpServers": {    "llm-cost": {      "command": "npx",      "args": ["-y", "@comparedge/llm-cost-mcp@latest"]    }  }}

Claude Desktop keeps this file at ~/Library/Application Support/Claude/claude_desktop_config.json. Cursor: Settings, then MCP. VS Code with Copilot reads .vscode/mcp.json. Restart the client; six tools appear. No API key, no account. Per-client walkthroughs live in the setup guide.

Family

Built by ComparEdge, where software prices are checked against vendor pages before anyone quotes them. Two siblings share the data: the full catalog server and a price-change watcher, both on ComparEdge MCP.

MIT licensed. JSON-RPC 2.0 over stdio, standard Model Context Protocol.

Source: README.md at commit c413e54

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Edge integrations

Edge Network

network.edgeOfficial publisher

Remote MCP server for Edge Network cloud: an assistant can deploy sites and apps, manage VMs, storage buckets, DNS, and Shield/Assist widgets on one account.

Streamable HTTPWeb executable
Cloud & Infrastructure28 toolsOct 24, 2026

Historical Edge

Published by GitHub account joachimglassell-ship-it

Remote MCP server that returns precomputed, source-traced historical equity study statistics for a supported study and horizon.

Streamable HTTPWeb executable
Finance1 toolNov 7, 2026

Edge Actors: email verifier, DNS facts, URL to Markdown

Published by GitHub account EdgeF-4

Apify-hosted remote MCP server offering email verification, SPF/DMARC/MX DNS lookups and URL-to-Markdown conversion on your own Apify account.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredNov 7, 2026

Betting Edge — NFL Elo Research

Published by GitHub account FedX19

Remote MCP server exposing archived NFL Elo forecasts, odds comparisons, ratings, calibration and graded records for betting research.

Streamable HTTPWeb executable
Finance7 toolsNov 1, 2026

ValuEdge Stock Research MCP

Published by GitHub account kkfir13

A read-only stock research server that gives an assistant ValuEdge search, fair-value, fundamentals, comparison and screening tools, plus the signed-in user's O

Streamable HTTPWeb executable
Finance9 toolsOct 25, 2026