Is this AI model id retired, when does it shut off, and what does its provider say replaces it?
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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".
The model id as the provider writes it. Matched exactly, then case-insensitively, then against the alternative name a record's own id prints, then against the human-readable model name. Never as a substring: "gpt-4" does not answer for "gpt-4o".
Optional. Narrow to one provider's schedule, matched case-insensitively as a substring of the provider name ("bedrock", "azure", "groq"). Leave it out to see every host's clock for this id, which is usually what you want.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http ai-model-retirement-dates https://referencesource.org/mcp/models
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".
| Argument | Type | Description |
|---|---|---|
| model_id* | string | The model id as the provider writes it. Matched exactly, then case-insensitively, then against the alternative name a record's own id prints, then against the human-readable model name. Never as a substring: "gpt-4" does not answer for "gpt-4o". |
| provider | string | Optional. Narrow to one provider's schedule, matched case-insensitively as a substring of the provider name ("bedrock", "azure", "groq"). Leave it out to see every host's clock for this id, which is usually what you want. |
{
"type": "object",
"required": [
"model_id"
],
"properties": {
"model_id": {
"type": "string",
"description": "The model id as the provider writes it. Matched exactly, then case-insensitively, then against the alternative name a record's own id prints, then against the human-readable model name. Never as a substring: \"gpt-4\" does not answer for \"gpt-4o\"."
},
"provider": {
"type": "string",
"description": "Optional. Narrow to one provider's schedule, matched case-insensitively as a substring of the provider name (\"bedrock\", \"azure\", \"groq\"). Leave it out to see every host's clock for this id, which is usually what you want."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| days | integer | How far ahead to look, in days from today (UTC). 90 by default. Pass 0 to get only what is already past its date. |
| limit | integer | How many to return, 1–20. Default 20. |
| provider | string | Optional case-insensitive substring of the provider name ("openai", "bedrock", "azure", "together"). |
| include_already_retired | boolean | Include models whose shutdown date has already passed. False by default: this tool answers "what is coming". Set true to audit pins that are already dead. |
{
"type": "object",
"properties": {
"days": {
"type": "integer",
"description": "How far ahead to look, in days from today (UTC). 90 by default. Pass 0 to get only what is already past its date."
},
"limit": {
"type": "integer",
"description": "How many to return, 1–20. Default 20."
},
"provider": {
"type": "string",
"description": "Optional case-insensitive substring of the provider name (\"openai\", \"bedrock\", \"azure\", \"together\")."
},
"include_already_retired": {
"type": "boolean",
"description": "Include models whose shutdown date has already passed. False by default: this tool answers \"what is coming\". Set true to audit pins that are already dead."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| field | string | Which field the claim is about, if you know it. Without it, every stored field of the record is checked. |
| model_id* | string | The model id the claim is about, matched the same way model_status matches it. Where more than one record holds the id, narrow with `provider` or `record_id` — the check is refused rather than run against whichever came first. |
| provider | string | Optional case-insensitive substring of the provider name, to pick which host's record the claim is checked against. |
| record_id | string | Optional. The exact record to check against, as model_status returns it in record_id. Settles the case where one provider holds the same id twice (AWS Bedrock publishes two schedules for claude-3-haiku, one per region group). |
| claimed_value* | string | The value to check, exactly as claimed, e.g. "Terminated" or "2026-10-29". |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 16, 2026.
{
"type": "object",
"required": [
"claimed_value",
"model_id"
],
"properties": {
"field": {
"type": "string",
"description": "Which field the claim is about, if you know it. Without it, every stored field of the record is checked."
},
"model_id": {
"type": "string",
"description": "The model id the claim is about, matched the same way model_status matches it. Where more than one record holds the id, narrow with `provider` or `record_id` — the check is refused rather than run against whichever came first."
},
"provider": {
"type": "string",
"description": "Optional case-insensitive substring of the provider name, to pick which host's record the claim is checked against."
},
"record_id": {
"type": "string",
"description": "Optional. The exact record to check against, as model_status returns it in record_id. Settles the case where one provider holds the same id twice (AWS Bedrock publishes two schedules for claude-3-haiku, one per region group)."
},
"claimed_value": {
"type": "string",
"description": "The value to check, exactly as claimed, e.g. \"Terminated\" or \"2026-10-29\"."
}
}
}