Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events.
Remote server: your requests and data go to modelmeter.xyz. Claude Code: claude mcp add --transport http modelmeter https://modelmeter.xyz/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
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 uget_model — Unified card for one model in a single call: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, resellist_models — List available models with their current pricing. Optionally filter by provider.get_price_history — Historical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.list_events — The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity tocheck_model_dependencies — Is my stack okay? Check a list of model ids against the record: scheduled retirements with days-remaining countdowns and migration targets, list_deprecations — Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.