LLM Cutover
Checks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.
Should I use this
Quality & Safety
B
Findings (1)
- LOWin list_models
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
~825Tokens (tool definitions)
~3.6 KBTypical response size
Moderate attention impact (0.64% of 128k context)
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"audit": {
"url": "https://api.llmcutover.com/mcp"
}
}
}Remote endpoints
https://api.llmcutover.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (2)
🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢run_cutover_audit(mode, question, fields, samples, current, ...)
Measures how often a cheaper model (Sage 2) agrees with your current LLM on your samples, the confidence threshold for routing, and the monthly cost now vs a hybrid. Returns the full report as JSON.
Input Schema
{
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"yesno",
"extract"
],
"description": "yesno: a yes/no decision per text. extract: fields pulled out of each text."
},
"question": {
"type": "string",
"maxLength": 600,
"description": "yesno only. The yes/no question your current model answers, e.g. \"Is this ticket about billing?\""
},
"fields": {
"type": "object",
"description": "extract only. Up to 12 fields: {\"name\": {\"type\": \"string|number|integer|boolean|date|money\", \"definition\": \"...\"}}",
"additionalProperties": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"string",
"number",
"integer",
"boolean",
"date",
"money"
]
},
"definition": {
"type": "string",
"maxLength": 300
}
}
}
},
"samples": {
"description": "Real inputs with the answer your CURRENT model gave. Array of objects or a JSONL/CSV string. yesno: {\"text\",\"label\":\"yes|no\"}; extract: {\"text\",\"expected\":{...}}. Each text ≤ 4000 chars. Min 5. Max 10 anonymous, 25 free on the website, 500 yesno / 200 extract with a pass.",
"oneOf": [
{
"type": "array",
"minItems": 5,
"items": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"label": {
"type": "string",
"enum": [
"yes",
"no"
]
},
"expected": {
"type": "object"
}
},
"required": [
"text"
]
}
},
{
"type": "string"
}
]
},
"current": {
"type": "object",
"description": "Your current model: {\"model\": \"<id from GET /api/models>\", \"effort\": \"<level>\"} or custom prices {\"in\": USD per 1M input tokens, \"out\": USD per 1M output tokens}.",
"properties": {
"model": {
"type": "string",
"enum": [
"claude-fable-5.1",
"claude-opus-5.5",
"claude-sonnet-5.5",
"claude-haiku-5.5",
"gpt-6-astra",
"gpt-5.6-sol",
"gpt-6.1-sol",
"gpt-6.1-terra",
"gpt-5-mini",
"gpt-6-luna",
"gemini-4-argon",
"gemini-3.8-flash",
"gemini-3.1-flash-lite"
]
},
"effort": {
"type": "string"
},
"in": {
"type": "number",
"minimum": 0,
"maximum": 1000
},
"out": {
"type": "number",
"minimum": 0,
"maximum": 1000
}
}
},
"target": {
"type": "number",
"enum": [
0.95,
0.98,
0.99
],
"default": 0.98,
"description": "Agreement you need on the calls the cheap model keeps."
},
"usage": {
"type": "object",
"properties": {
"monthlyCalls": {
"type": "integer",
"minimum": 0,
"maximum": 1000000000,
"default": 100000
},
"promptOverheadTokens": {
"type": "integer",
"minimum": 0,
"maximum": 20000,
"default": 400
},
"outputTokens": {
"type": "integer",
"minimum": 0,
"maximum": 4000
},
"reasoningTokens": {
"type": "integer",
"minimum": 0,
"maximum": 50000,
"description": "Measured reasoning tokens per call, if you know them; otherwise estimated from effort."
}
}
}
},
"required": [
"mode",
"samples",
"current"
]
}🟢list_models
Current models with $/1M token prices and effort levels, usable as current.model.
Input Schema
{
"type": "object",
"properties": {}
}Community
Evidence
Recent observations
verifiedversion not recorded2 tools