AI model deprecation and retirement dates, by provider
Server Details
Is this AI model id retired, when does it shut off, and what does its provider say replaces it?
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools target distinct query shapes: a single-id lookup, a time-windowed sweep, and a claim check. model_status and verify_quote both return the same stored fields for a given id, so an agent could plausibly reach for verify_quote just to read a date, but the descriptions clearly frame verify_quote as claim validation and steer callers to model_status for plain facts.
All snake_case and uniformly readable, but two names are bare noun phrases (model_status, upcoming_retirements) while the third is verb_noun (verify_quote), so the verb pattern is not fully predictable. Minor deviation, not confusing.
Three tools is tight but each maps to a genuinely different question an agent asks (what is this id, what is expiring, is this claim true). Nothing is redundant; the surface is slightly thin for the breadth of the record set it sits on.
Lookup, upcoming-window, and verification are covered, but there is no discovery path: no way to search by partial id or family, or to enumerate all records for a provider. Since model_status returns found:false for unknown ids, an agent that does not already know the exact id string cannot get into the dataset.
Available Tools
3 toolsmodel_statusIs this AI model id retired, and when does it shut off?ARead-onlyInspect
Ask this before you pin, recommend or migrate off a model id. Give the id exactly as it goes in the config — "gpt-4o", "anthropic.claude-3-haiku-20240307-v1:0", "gemini-1.5-pro-002", "mistral-large-2407" — and get whether it is retired, the shutdown date the provider published, the replacement the provider names, and a verbatim quote of the page that says so. Where several hosts sell the same id you get every one of them, and earliest_announced_shutdown is the date a migration actually has to meet: on 34 records a second host switches the model off EARLIER than the record's primary source does. An id we hold nothing for returns found: false and no date, which means not in our records, never "still supported".
Inputs: model_id (required), provider. Returns: as_of, found, answer, models, +7 more
upcoming_retirementsWhich AI models shut off in the next N days?ARead-onlyInspect
What is about to break? Lists the model ids whose provider has published a shutdown date inside the next N days, soonest first, each with the provider, the replacement it names and a verbatim quote. Use it to sweep a codebase's pins before they bite, or to see what a quarter's migration work looks like. Optionally narrowed to one provider. Dates a provider printed as a floor ("not sooner than") are deliberately left out and counted in the response, because such a model could go years later and listing it here would be a guess.
Inputs: days, limit, provider, include_already_retired. Returns: to, from, as_of, models, +6 more
verify_quoteCheck a claimed model retirement date against the registerARead-onlyInspect
Is this right? Check a claim about a model id — its shutdown date, its lifecycle status, the replacement it was given — against the provider's own record instead of trusting it. Says whether the claim equals a stored value, appears only in the verbatim quote, or differs (and then what the record says instead). A model retirement date recalled from memory is exactly the kind of confident wrong answer that leaves a config pinned to something that stopped answering.
Inputs: model_id (required), claimed_value (required), field, provider, +1 more. Returns: match, record, verdict, attestation, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI model shutdown dates, replacements, and migration diffs. Free, no API key.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
Is this model or API still safe to call? Retirement and breaking change dates, with the fix.
Related MCP Servers
- AlicenseAqualityCmaintenanceCheck whether an LLM model id is deprecated, retiring, or retired, and what to migrate to. Covers OpenAI, Anthropic, Azure, Bedrock, Google, and Cohere from each provider's own deprecation pages.5176 npm1MIT
- FlicenseNot gradedqualityCmaintenanceEnables querying AI model lifecycle and deprecation data across OpenAI, Anthropic, Google Gemini, and Amazon Bedrock, including model status, sunset dates, and recommended replacements via MCP tools.-
- AlicenseAqualityBmaintenanceChecks OpenAI, Anthropic and Google model IDs for retirement: status, retirement date, days left and replacement, from the providers' deprecation pages, re-checked daily. Can also scan a project folder for retired or retiring model IDs with file and line, and list what retires in the next N days. No API key needed.233,835 npm1Elastic 2.0
- AlicenseNot gradedqualityBmaintenanceEnables querying a single normalised, deduplicated feed of AI model releases, price changes, API changes and deprecations across vendor notes, Hugging Face, OpenRouter, GitHub and the LiteLLM price map. Also supports model lookup by budget, context and capability, side-by-side comparisons, monthly cost estimates in USD and KRW, and ranked replacement suggestions when a model goes away.293 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.