LLM Model ID Check is an MCP server published by ai.opencurrent, hosted at opencurrent.ai. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including check_model_id, latest_models.
Check if an LLM model ID is current and find newer models (Anthropic, OpenAI, Google and more).
28 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Is this model ID current? Returns the model (release date, knowledge cutoff, context and output limits, price per million tokens) and newer models in the same family, or close suggestions if the ID is unknown.
| Parameter | Type | Description |
|---|---|---|
| model_id * | string |
{
"name": "check_model_id",
"title": "Check an LLM model ID",
"description": "Is this model ID current? Returns the model (release date, knowledge cutoff, context and output limits, price per million tokens) and newer models in the same family, or close suggestions if the ID is unknown.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model_id"
],
"properties": {
"model_id": {
"type": "string",
"maxLength": 120,
"minLength": 2
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"exists"
],
"properties": {
"exists": {
"type": "boolean"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Newest models of a provider, optionally filtered by a word such as 'sonnet', 'mini' or 'flash'.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| filter | string | |
| provider * | string | one of ["anthropic","openai","google","mistral","deepseek","xai"] |
{
"name": "latest_models",
"title": "Latest models of a provider",
"description": "Newest models of a provider, optionally filtered by a word such as 'sonnet', 'mini' or 'flash'.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"provider"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 30,
"minimum": 1
},
"filter": {
"type": "string",
"maxLength": 40
},
"provider": {
"enum": [
"anthropic",
"openai",
"google",
"mistral",
"deepseek",
"xai"
],
"type": "string"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"models"
],
"properties": {
"models": {
"type": "array",
"items": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
}
}
}
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Before writing code that calls an LLM API (Anthropic, OpenAI, Google, Mistral, DeepSeek, xAI), check that the model ID you remember still exists and whether a newer model in the same family is out. Data: models.dev (MIT), refreshed hourly.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.