xyz.modelmeter/modelmeter

Official7 tools

by modelmeters · JavaScript

Modelmeter

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

Tracks AI model lifecycle events including deprecations, pricing changes, and sunsets.

Topics

aiai-agentsllmllm-tools

Captured live from the server via tools/list.

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.

Parameters (3)

modelstringrequired
Model id in provider/model form, e.g. anthropic/claude-opus-4-8. Use list_models to discover ids.
input_tokensintegerrequired
Number of input (prompt) tokens.
output_tokensintegerrequired
Number of output (completion) tokens.

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).

Parameters (1)

idstringrequired
Model id in provider/model form, e.g. openai/gpt-5-5.

list_models

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

Parameters (3)

providerstring
Provider id, e.g. anthropic, openai, google, venice, openrouter.
include_unavailableboolean
Include deprecated/restricted/unavailable models. Default false.
limitinteger
Max rows to return. Default 200.

get_price_history

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

Parameters (4)

modelstring
Model id to fetch history for.
providerstring
Provider id to fetch history for (all its models).
sincestring
ISO date (YYYY-MM-DD); only points on/after this date.
untilstring
ISO date (YYYY-MM-DD); only points on/before this date.

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).

Parameters (7)

providerstring
Filter to events touching this provider.
typestring
Event type, e.g. model_deprecation, pricing_change, model_launch.
severitystring
Filter by what the event demands of consumers of the affected models.
statusstring
Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified.
sincestring
ISO date (YYYY-MM-DD); events announced on/after.
untilstring
ISO date (YYYY-MM-DD); events announced on/before.
limitinteger
Max events. Default 50.

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.

Parameters (1)

modelsarrayrequired
Model ids to check, e.g. ["gpt-4o", "claude-sonnet-4-6", "gemini-2.5-flash"].

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.

Parameters (3)

providerstring
Filter to one provider id.
statusstring
Default scheduled.
limitinteger
Max rows. Default 100.

README.md5 KBView on GitHub

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:

code

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.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "modelmeter": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://modelmeter.xyz/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.