Skip to main content
Glama

AI model deprecation and retirement dates, by provider

Is this AI model id retired, and when does it shut off?

model_status
Read-only

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".

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model_id": "<model_id>"
    },
    "name": "model_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYesThe 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".
providerNoOptional. 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.

Output Schema

NameRequiredDescriptionDefault
as_ofYesThe UTC date every "has it passed" answer here was computed against.
foundYes
answerNoOne sentence, computed here from the records below, for a caller that needs a line rather than a structure.
modelsNo
coverageYes
registerNo
matched_onNoWhich rung of the ladder matched. Absent when nothing did.
records_foundYes
model_id_askedYes
similar_ids_in_our_recordsNoOnly on a miss. Ids in this register containing the string you asked about. NOT AN ANSWER about any of them — no date and no status is attached, because you did not ask about them. Call model_status again with one if it is the id you meant.
earliest_announced_shutdownNoThe soonest shutdown date any source states for this id, with the page and quote that state it. THE FIGURE TO PLAN AGAINST. Floors and no-date sentences are excluded; null where no source gives a date. A negative days_away means at least one host has already switched the model off.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly=true and openWorld=false, and the description genuinely adds semantics beyond them: multi-host records, the earliest_announced_shutdown field, and the crucial found:false interpretation. However, it embeds this in a long prose paragraph rather than structured guidance, and does not discuss matching failure modes beyond the schema's own field description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the actionable instruction and free of filler, but the body is a single dense paragraph with em-dash asides and multiple example ids that slow scanning. It would read better as short separated clauses, though every sentence does carry information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the edge case an agent would otherwise get wrong (no record means not-in-records, not still-supported), explains the multi-host date semantics, and an output schema already documents return shape. Nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description exceeds it by explaining the provider parameter's omission behavior — leaving it out returns every host's clock for the id — and by emphasizing exact-id entry with concrete provider-formatted examples. That is real meaning added beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource: tells whether a model id is retired, its published shutdown date, the provider's named replacement, and a verbatim citation. The scope is unmistakable and an agent can distinguish it from a list-style sibling like upcoming_retirements without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit timing guidance — "Ask this before you pin, recommend or migrate off a model id" — which is a concrete trigger condition. It does not name alternatives or state when NOT to use it (e.g., bulk listing vs. single-id lookup), so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources