AIモデルインテリジェンス

機能 · 2026-11-12

Tool calling に対応した AI モデル

ツール呼び出し / 関数呼び出しに対応する AI モデルの比較 —— エージェントと自動化に最適。

これは何か

  • Tool calling(function calling)により、LLM が構造化 JSON で外部関数(検索・コード実行・DB クエリなど)の呼び出しを生成できます。
  • モデルは関数名と引数を JSON で返し、ランタイムが実行して結果をツールメッセージとして戻します。

なぜ重要か

  • ツール呼び出しがないと、エージェントは自由文を正規表現で解析する必要があり壊れやすいです。
  • RAG、ReAct ループ、多段アシスタントを本番で安定させるのは Tool calling です。

この機能に対応するモデル 1475 件

モデルベンダー入力 / 1M出力 / 1Mコンテキストプロバイダー
Qwen3.8 27BAlibaba (Qwen)$0.001$0.0011.05M51
Ambient Smallambient$0.001$0.001101K1
Gemma 4 26B A4B ITGoogle$0.010$0.031262K23
Llama-3.1-8B-InstructMeta$0.020$0.030131K14
Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030128K1
Mistral NemoMistral$0.029$0.030131K6
inclusionAI: Ling 3.0 Tinykilo$0.015$0.045262K1
Ling 3.0 Tinynano-gpt$0.015$0.045262K1
Ling 3.0 Tiny Thinkingnano-gpt$0.015$0.045262K1
Ling 3.0 Tinyopenrouter$0.015$0.045262K1
Ministral 3Bazure-cognitive-services$0.040$0.040128K1
Ministral 3Bazure$0.040$0.040128K1
Ling 3.0 Flashvercel$0.021$0.063256K1
Ling 3.0 Flashopenrouter$0.021$0.063262K1
Qwen3.5 9BAlibaba (Qwen)$0.040$0.060262K21
gpt-oss-20bOpenAI$0.018$0.090131K32
Qwen3.5 4BAlibaba (Qwen)$0.040$0.070262K5
GLM Flash LatestZ.AI / Zhipu$0.040$0.0781.05M4
Granite 4.0 H Microcloudflare-workers-ai$0.017$0.112131K1
Llama 3.1 8BMeta$0.050$0.080131K2
DeepSeek V4 Flash 0731DeepSeek$0.045$0.0901.05M54
Model Routerazure-cognitive-services$0.140Unknown200K1
Model Routerazure$0.140Unknown200K1
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.025$0.120262K5
DeepSeek-V4.1-FlashDeepSeek$0.030$0.1201M72
DeepSeek V4.1 Flash 1017DeepSeek$0.030$0.1201.05M60
Qwen3.7 FlashAlibaba (Qwen)$0.030$0.1301M13
DeepSeek R1 Distill Llama 70BMeta$0.030$0.130128K2
Amazon: Nova Micro 1.0kilo$0.035$0.140128K1
Nova Microvercel$0.035$0.140128K1
Nova Micro (US)amazon-bedrock$0.035$0.140128K1
Nova Microamazon-bedrock$0.035$0.140128K1
Nova Micro (US)edenai$0.035$0.140128K1
Nova Microedenai$0.035$0.140128K1
Nova Micro 1.0openrouter$0.035$0.140128K1
amazon--nova-microsap-ai-core$0.035$0.140128K1
gpt-oss-120bOpenAI$0.030$0.150131K51
Ling 3.1 Flashopenrouter$0.045$0.1351M1
Nova Micro (APAC)amazon-bedrock$0.037$0.148128K1
Nova Micro 1.0aimlapi$0.037$0.148128K1
Command R7BCohere$0.037$0.150128K6
Command R7B ArabicCohere$0.037$0.150128K1
Qwen3 235B A22B Instruct 2507Alibaba (Qwen)$0.090$0.100262K22
Mercury 2.5 Previewinception$0.040$0.150260K1
GPT OSS 20Bkenari$0.036$0.154131K1
Trinity Miniclarifai$0.045$0.150131K1
Nova Micro 1.0cortecs$0.040$0.159128K1
Ministral 3 3BMistral$0.100$0.100131K8
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.050$0.150262K7
nemotron-3-ultraNVIDIA$0.100$0.100262K3
Reka Edge 2603 (reka-ai)llmgateway-providers$0.100$0.10016K1
Reka Edgekilo$0.100$0.10016K1
Ministral 3B (latest)Mistral$0.100$0.100131K1
Nova Micro (EU)amazon-bedrock$0.040$0.160128K1
Reka Edge 2603llmgateway$0.100$0.10016K1
GPT OSS 120Bsynthetic$0.100$0.100131K1
Reka Edgeopenrouter$0.100$0.10016K1
Sarvam 105Bfastrouter$0.040$0.160131K1
IBM: Granite 4.2 8Bkilo$0.060$0.150131K1
Granite 4.2 8Bnano-gpt$0.060$0.150131K1

全 1475 件中、上位 60 件を表示。 さらに絞り込むには モデル一覧 をご利用ください。

Frequently asked questions

How many AI models support ツール呼び出し?

1475 canonical models in our database currently support ツール呼び出し. The list is regenerated on every data refresh, so it always reflects the latest releases tracked in our catalogue.

What is the cheapest model with ツール呼び出し?

Qwen3.8 27B from Alibaba (Qwen) is currently the lowest-priced option, at $0.001 per 1M input tokens and $0.001 per 1M output tokens. The full table above is sorted price-ascending.

Which model with ツール呼び出し has the largest context window?

Llama 4 Scout 17B Instruct (US) (Meta) leads on context at 10M tokens. This may matter if you also need long-document understanding alongside ツール呼び出し.

Which models are available on the most providers?

Production-readiness usually correlates with how many independent providers host the same weights. The top three by provider count are: GLM-5.3-Flash (92), GLM-5.3 (92), GLM-5.2 (90).

How is ツール呼び出し different from a regular LLM?

Tool calling lets the model emit a structured JSON request to invoke an external function (search, code execution, DB query) instead of replying with prose. Without it, agents must parse freeform text — fragile and slow.

How often is this list updated?

Daily. Our data pipeline syncs once a day, regenerates the canonical model list, and rebuilds these pages so newly released models appear within 24 hours.

最終更新:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.