Modelmeter
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events.
| Author | xyz.modelmeter |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2015 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Modelmeter": {
"url": "https://modelmeter.xyz/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (7)
estimate_costEstimate 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:
model(required) — string — Model id in provider/model form, e.g. anthropic/claude-opus-4-8. Use list_models to discover ids.input_tokens(required) — integer — Number of input (prompt) tokens.output_tokens(required) — integer — Number of output (completion) tokens.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_modelUnified 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:
id(required) — string — Model id in provider/model form, e.g. openai/gpt-5-5.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_modelsList available models with their current pricing. Optionally filter by provider.
Parameters:
limit— integer — Max rows to return. Default 200.provider— string — Provider id, e.g. anthropic, openai, google, venice, openrouter.include_unavailable— boolean — Include deprecated/restricted/unavailable models. Default false.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_price_historyHistorical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.
Parameters:
model— string — Model id to fetch history for.since— string — ISO date (YYYY-MM-DD); only points on/after this date.until— string — ISO date (YYYY-MM-DD); only points on/before this date.provider— string — Provider id to fetch history for (all its models).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_eventsThe 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:
type— string — Event type, e.g. model_deprecation, pricing_change, model_launch.limit— integer — Max events. Default 50.since— string — ISO date (YYYY-MM-DD); events announced on/after.until— string — ISO date (YYYY-MM-DD); events announced on/before.status— string — Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified.provider— string — Filter to events touching this provider.severity— string — Filter by what the event demands of consumers of the affected models.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
check_model_dependenciesIs 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:
models(required) — array — Model ids to check, e.g. ["gpt-4o", "claude-sonnet-4-6", "gemini-2.5-flash"].
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_deprecationsPer-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:
limit— integer — Max rows. Default 100.status— string — Default scheduled.provider— string — Filter to one provider id.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.