AgentKernel AI model data
Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'estimate_cost' description lacks action verbestimate_cost 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"models": {
"url": "https://www.agentkernel.si/mcp"
}
}
}リモートエンドポイント
https://www.agentkernel.si/mcpstreamable-httpできること
ツール一覧
ツール（6）
🟢best_for_task(task, license, limit)
Ranks AI models for one task by performance only (price shown, never used for the rank). Tasks cover text, coding, agents, websites/UI/games/data viz, image generation and editing, video from text or image, video editing, text to speech, transcription, music and embeddings.
入力スキーマ
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"overall",
"coding",
"agents",
"websites",
"ui-components",
"game-development",
"data-visualization",
"3d-scenes",
"svg-graphics",
"web-apps",
"full-stack",
"mobile-apps",
"image-generation",
"image-editing",
"graphics-and-logos",
"text-to-video",
"image-to-video",
"video-editing",
"text-to-speech",
"transcription",
"music",
"embeddings"
],
"description": "Task slug"
},
"license": {
"type": "string",
"enum": [
"all",
"open",
"closed"
],
"default": "all",
"description": "open = open weights only, closed = proprietary only"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"default": 10
}
},
"required": [
"task"
],
"additionalProperties": false
}🟢recommend_models(use_case, monthly_budget_usd, priority, input_tokens, output_tokens, ...)
Returns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional privacy and licence requirements.
入力スキーマ
{
"type": "object",
"properties": {
"use_case": {
"type": "string",
"enum": [
"everyday",
"coding",
"agents",
"documents"
]
},
"monthly_budget_usd": {
"type": "number",
"minimum": 0,
"default": 10
},
"priority": {
"type": "string",
"enum": [
"balanced",
"quality",
"saving"
],
"default": "balanced"
},
"input_tokens": {
"type": "integer",
"minimum": 0,
"default": 1000000,
"description": "Input tokens per month"
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"default": 250000,
"description": "Output tokens per month"
},
"privacy": {
"type": "string",
"enum": [
"any",
"zdr",
"eu"
],
"default": "any",
"description": "zdr = zero data retention, eu = zero retention in an EU region"
},
"open_weights_only": {
"type": "boolean",
"default": false
},
"needs_vision": {
"type": "boolean",
"default": false
},
"include_free": {
"type": "boolean",
"default": false
}
},
"required": [
"use_case"
],
"additionalProperties": false
}🟢get_model(model, input_tokens, output_tokens)
Price, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.
入力スキーマ
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id like \"anthropic/claude-opus-5.5\" or a name like \"Claude Opus 5.5\""
},
"input_tokens": {
"type": "integer",
"minimum": 0,
"default": 1000000
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"default": 250000
}
},
"required": [
"model"
],
"additionalProperties": false
}🟢find_models(query, license, privacy, sort, limit)
Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Part of a name, id or provider"
},
"license": {
"type": "string",
"enum": [
"all",
"open",
"closed"
],
"default": "all"
},
"privacy": {
"type": "string",
"enum": [
"any",
"zdr",
"eu"
],
"default": "any"
},
"sort": {
"type": "string",
"enum": [
"performance",
"coding",
"agentic",
"price",
"context"
],
"default": "performance"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"default": 10
}
},
"additionalProperties": false
}🟢estimate_cost(models, input_tokens, output_tokens)
Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.
入力スキーマ
{
"type": "object",
"properties": {
"models": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 5
},
"input_tokens": {
"type": "integer",
"minimum": 0,
"default": 1000000
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"default": 250000
}
},
"required": [
"models"
],
"additionalProperties": false
}🟢cheaper_alternative(model, input_tokens, output_tokens)
For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.
入力スキーマ
{
"type": "object",
"properties": {
"model": {
"type": "string"
},
"input_tokens": {
"type": "integer",
"minimum": 0,
"default": 1000000
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"default": 250000
}
},
"required": [
"model"
],
"additionalProperties": false
}コミュニティ
エビデンス