Modelmeter

xyz.modelmeterPublished by modelmeter.xyzOfficial publisherv1.0.0Updated Oct 24, 2026

The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Remote MCP server exposing a verified record of LLM model pricing, deprecations and changelog events, plus token cost estimates.

What you can do
  • List models and read a unified model card with normalized pricing, capabilities and price-history summary
  • Estimate the USD cost of an LLM API call for given token counts, including reseller markup vs. upstream
  • Retrieve historical pricing time-series for a model or provider
  • Browse the changelog of deprecations, price changes, launches and market events, filterable by severity
  • Check a list of model ids for scheduled retirements, days remaining and migration targets
  • List per-model retirement rows sorted by shutdown date
When to use it
Useful when an assistant needs current or historical LLM pricing, wants to estimate API call costs, or must check whether models in a stack are deprecated, sunsetting or already retired before recommending or migrating them.
Requirements
A remote Streamable HTTP endpoint; no authentication, install or API key is required. The client must support remote MCP servers over HTTP.
Before you install
Read-only lookups; no data is written or changed. Pricing and event data come from a third party and are described as human-verified, but cost estimates should be treated as informational rather than billing-grade.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/xyz.modelmeter%2Fmodelmeter/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "modelmeter": {
      "type": "http",
      "url": "https://modelmeter.xyz/mcp"
    }
  }
}

README

Modelmeter

The changelog of record for the AI stack. Live at modelmeter.xyz.

What this is

A machine-readable, source-verified record of everything that changes in the model layer: deprecations with sunset dates and migration targets, silent model swaps behind stable IDs, price changes, releases — plus three years of pricing history and cost tooling. Every event carries its sources with verbatim quotes (most with archive snapshots), a verification status (unverified → human-reviewed verified), and corrections are never silent — a correction event points at what it supersedes.

Built primarily for AI agents to call programmatically, secondarily for humans through a dashboard. Reach it three ways: plain GET URLs returning JSON, a remote MCP server any tool-calling agent can connect to, and a visual dashboard built on the same endpoints. The wedge: clean URLs, stable JSON contracts, an OpenAPI spec, and an llms.txt discoverability file. Most sites in this space are JS-heavy SPAs that agents can't use; Modelmeter is built the other way around.

Endpoints

  • GET /estimate?model=X&input=N&output=M — token cost for a hypothetical call, including upstream-markup comparison for reseller models
  • GET /models — current model catalog, with filters
  • GET /model?id=X — unified card for one model: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, reseller markup, and a price-history summary (launch vs. current price, % change, all-time low/high)
  • GET /check?models=gpt-4o,claude-sonnet-4-6 — is my stack okay? Verdict per model: scheduled retirements with days-remaining and migration targets, past retirements, breaking changes, or a clean bill
  • GET /deprecations — per-model retirement rows: which model dies when, with runway and migration target
  • GET /feed.xml / GET /feed.json — RSS 2.0 / JSON Feed 1.1 of breaking and action-required events
  • GET /events — the changelog of record: deprecations, price changes, launches and surrounding market events, each with severity (breaking | action_required | informational), announced_at/effective_at dates, sources with quotes, and verification status. Filters: provider, type, model, severity, since, until, status
  • GET /history — historical pricing time-series per model, with filters
  • GET /pricing.json — raw pricing snapshot
  • GET /events.json — raw events snapshot
  • GET /history.json — raw historical time-series

See public/openapi.yaml for the full spec.

GitHub Action

Fail CI when a model your repo depends on is deprecated, sunsetting, or already retired:

yaml
- uses: modelmeters/modelmeter/actions/check@main  # with:  #   models: "gpt-4o, claude-sonnet-4-6"   # optional — otherwise the repo is scanned for known model ids  #   fail-on: breaking                      # breaking (default) | retired | none  #   warn-days: "120"                       # sunsets within N days fail; beyond N warn

The action scans your repo for known model ids (catalog + every model named in a deprecation event, dashed and dotted spellings), calls /check, annotates the exact file:line of each affected model, writes a job-summary table with migration targets, and exits nonzero per your fail-on policy.

MCP server

Modelmeter is also a remote MCP server, so any tool-calling agent (Claude, Hermes, …) can call it natively over the Streamable HTTP transport — no auth, no install:

https://modelmeter.xyz/mcp

Tools: check_model_dependencies, list_deprecations, estimate_cost, get_model, list_models, get_price_history, list_events. Start with list_models to discover ids, then get_model or estimate_cost. The MCP tools return the same data as the REST endpoints above — use whichever your runtime prefers.

Datasets

  • pricing/ — current and historical model pricing across providers
  • events/ — the events record (schema 2.0.0): deprecations, price changes, releases, and market events with primary-source citations, verbatim quotes, and verification status

Each entry carries a last_verified date. Daily snapshots in pricing/snapshots/ accumulate the historical record. Wrong pricing is the existential risk — the schema requires explicit human verification before an entry is served.

Contributing

Found a price change? Open a PR updating pricing/current.json with the new value, an updated last_verified date, and the source URL.

Spotted a meaningful AI market event? Add an entry to events/current.json with primary-source citations and verified: true.

Automation opens issues when provider pricing pages change. Pick one up if you want to help.

License

MIT — see LICENSE.

Source: README.md at commit 5c026a1

Tools

7

estimate_cost

Estimate the USD cost of an LLM API call for a given model and token counts. Returns input/output/total cost, plus reseller markup vs. the upstream model when applicable.

Parametersmodelrequiredinput_tokensrequiredoutput_tokensrequired

get_model

Unified card for one model in a single call: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, reseller markup vs. upstream, and a price-history summary (launch vs. current price, percent change, last change date, all-time low/high).

Parametersidrequired

list_models

List available models with their current pricing. Optionally filter by provider.

Parameterslimitproviderinclude_unavailable

get_price_history

Historical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.

Parametersmodelsinceuntilprovider

list_events

The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, funding).

Parameterstypelimitsinceuntilstatusproviderseverity

check_model_dependencies

Is my stack okay? Check a list of model ids against the record: scheduled retirements with days-remaining countdowns and migration targets, past retirements, and other breaking/action-required changes. Id matching tolerates dots vs dashes, dated snapshot suffixes, and bare or provider-prefixed forms. Call this at startup or in CI with the models you depend on.

Parametersmodelsrequired

list_deprecations

Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date.

Parameterslimitstatusprovider

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

100% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts