AIモデルインテリジェンス

機能 · 2026-08-13

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 981 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
Voxtral Small 24B 2507Mistral$0.002$0.00232K4
Ling-2.6-flashopenrouter$0.010$0.030262K1
Llama 3.1 8B InstructMeta$0.020$0.030131K18
Mistral Nemo Instruct 2407Mistral$0.020$0.030131K7
Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030128K1
Ministral 3Bazure-cognitive-services$0.040$0.040128K1
Ministral 3Bazure$0.040$0.040128K1
Ministral 3B (latest)Mistral$0.040$0.040128K1
Ling-3.0-flashopenrouter$0.021$0.063262K1
L3 8B Stheno V3.2novita-ai$0.050$0.0508K1
Qwen3.5 4BAlibaba (Qwen)$0.040$0.07033K3
Gemma 3 4B ITGoogle$0.040$0.080128K5
Gemma 4 E4B ITGoogle$0.020$0.100131K3
Sarvam 30Bfastrouter$0.020$0.100128K1
Nex N2 Mininano-gpt$0.025$0.100262K1
Nex-N2-Miniopenrouter$0.025$0.100262K1
Nex AGI: Nex-N2-Minikilo$0.025$0.100262K1
Granite 4.0 H Microcloudflare-workers-ai$0.017$0.112131K1
Llama 3.1 8BMeta$0.050$0.080131K2
amazon--nova-microsap-ai-core$0.030$0.100128K1
Sarvam 30Bnano-gpt$0.028$0.11166K1
Model Routerazure-cognitive-services$0.140Unknown200K1
Model Routerazure$0.140Unknown200K1
Qwen3.7 FlashAlibaba (Qwen)$0.030$0.1181M9
Granite 4.1 8Bnano-gpt$0.050$0.100131K1
Granite 4.1 8Bopenrouter$0.050$0.100131K1
IBM: Granite 4.1 8Bkilo$0.050$0.100131K1
Mellum2 12B A2.5Bwandb$0.050$0.100131K1
Granite 4.1 8Bwandb$0.050$0.100131K1
gpt-oss-20bOpenAI$0.030$0.130128K28
DeepSeek R1 Distill Llama 70BMeta$0.030$0.13033K3
GPT OSS 120Bllmgateway$0.032$0.140131K1
Nova Micro 1.0openrouter$0.035$0.140128K1
Nova Microamazon-bedrock$0.035$0.140128K1
Nova Microvercel$0.035$0.140128K1
Amazon: Nova Micro 1.0kilo$0.035$0.140128K1
Laguna XS 2.1openrouter$0.060$0.120262K1
Command R7BCohere$0.037$0.150128K4
Command R7B ArabicCohere$0.037$0.150128K1
Qwen3.5 9BAlibaba (Qwen)$0.040$0.150262K22
GPT OSS 20Bllmgateway$0.040$0.150131K1
Trinity Miniclarifai$0.045$0.150131K1
nova-micro-v1cortecs$0.040$0.159128K1
gpt-oss-120bOpenAI$0.030$0.170128K43
Ministral 3 3B 2512Mistral$0.100$0.100131K3
GPT OSS 120Bsynthetic$0.100$0.100131K1
Reka Edgeopenrouter$0.100$0.10016K1
Sarvam 105Bfastrouter$0.040$0.160131K1
Ministral 8B (latest)Mistral$0.100$0.100128K1
Reka Edgekilo$0.100$0.10016K1
GPT OSS 20Bcortecs$0.045$0.167131K1
Mistral-7B-Instruct-v0.3Mistral$0.110$0.11066K5
Sarvam 105Bnano-gpt$0.045$0.177131K1
ministral-3b-2512cortecs$0.111$0.111256K1
Qwen Doc TurboAlibaba (Qwen)$0.087$0.144131K1
Google Gemma 3 27B InstructGoogle$0.080$0.160203K11
Ling 3.0 Flashvercel$0.060$0.180256K1
InclusionAI Ling 3.0 Flashllmgateway$0.060$0.180262K1
Ling-3.0-flashkilo$0.060$0.180262K1
Qwen3 30B A3B Instruct 2507Alibaba (Qwen)$0.048$0.193262K12

全 981 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?

981 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?

Voxtral Small 24B 2507 from Mistral is currently the lowest-priced option, at $0.002 per 1M input tokens and $0.002 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?

Qwen Long (Alibaba (Qwen)) 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-5.2 (74), Kimi K2.6 (62), DeepSeek V4 Pro (55).

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.