AI 模型情報

能力 · 2026-09-29

支援 Tool calling 的 AI 模型

對比支援工具呼叫 / 函式呼叫的 AI 模型 —— 適合搭建 Agent 與自動化流程。

這是什麼?

  • Tool calling(也稱 function calling)讓 LLM 以結構化 JSON 發出請求,呼叫你暴露的外部函式 —— 搜尋、程式碼執行、資料庫查詢等。
  • 模型回傳函式名稱與參數 JSON;你的執行環境執行後,再把結果以 tool message 回傳給模型。

為什麼重要

  • 沒有 tool calling 時,Agent 往往只能靠脆弱的正規表達式去解析自由文字。
  • Tool calling 是讓 RAG、ReAct 迴圈與多步助手在生產環境可靠運行的關鍵。

1380 個模型支援此能力

模型廠商輸入 / 1M輸出 / 1M上下文服務商
Voxtral Small 24B 2507Mistral$0.002$0.00233K5
GLiNER 2.5 Basepioneer$0.030Unknown4K1
Llama-3.1-8B-InstructMeta$0.020$0.030131K17
Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030128K1
Ministral 3Bazure$0.040$0.040128K1
Ministral 3Bazure-cognitive-services$0.040$0.040128K1
Ministral 3B (latest)Mistral$0.040$0.040128K1
Ling 3.0 Flash VLopenrouter$0.021$0.062262K1
Ling 3.0 Flashopenrouter$0.021$0.063262K1
Ling 3.0 Flashvercel$0.021$0.063256K1
L3 8B Stheno V3.2novita-ai$0.050$0.0508K1
DeepSeek V4 Flash 0731DeepSeek$0.035$0.0701.31M47
gpt-oss-20bOpenAI$0.018$0.090131K30
Qwen3.5 4BAlibaba (Qwen)$0.040$0.070262K3
GPT OSS 20B (FlexAI)edenai$0.020$0.100131K2
Sarvam 30Bfastrouter$0.020$0.100128K1
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
Model Routerazure$0.140Unknown200K1
Model Routerazure-cognitive-services$0.140Unknown200K1
Mellum2 12B A2.5Bwandb$0.050$0.100131K1
Granite 4.1 8Bwandb$0.050$0.100131K1
Qwen3.7 FlashAlibaba (Qwen)$0.030$0.1301M13
DeepSeek R1 Distill Llama 70BMeta$0.030$0.130128K3
GPT OSS 120Bllmgateway$0.032$0.140131K1
Amazon: Nova Micro 1.0kilo$0.035$0.140128K1
Nova Micro 1.0openrouter$0.035$0.140128K1
Nova Microvercel$0.035$0.140128K1
Nova Microedenai$0.035$0.140128K1
Nova Micro (US)edenai$0.035$0.140128K1
Nova Microamazon-bedrock$0.035$0.140128K1
Nova Micro (US)amazon-bedrock$0.035$0.140128K1
Laguna XS 2.1openrouter$0.060$0.120262K1
Nova Micro (APAC)amazon-bedrock$0.037$0.148128K1
Command R7BCohere$0.037$0.150128K5
Command R7B ArabicCohere$0.037$0.150128K1
Qwen3.5 9BAlibaba (Qwen)$0.040$0.150262K23
Mercury 2.5inception$0.040$0.150260K4
Mercury 2.5 Previewinception$0.040$0.150260K1
Trinity Miniclarifai$0.045$0.150131K1
nova-micro-v1cortecs$0.040$0.159128K1
gpt-oss-120bOpenAI$0.030$0.170131K47
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.050$0.150262K6
Ministral 3 3B 2512Mistral$0.100$0.100131K4
GPT OSS 120B (FlexAI)edenai$0.030$0.170131K4
Nemotron 3 Ultra 550B A55BNVIDIA$0.100$0.100131K3
Llama 3.2 3BMeta$0.100$0.100128K2
Agnes 3.0 Flashnano-gpt$0.050$0.150524K1
Space Bunny Alphanano-gpt$0.050$0.1501M1
Reka Edgekilo$0.100$0.10016K1
Reka Edgeopenrouter$0.100$0.10016K1
Sarvam 105Bfastrouter$0.040$0.160131K1
Ministral 3Bpioneer$0.100$0.100128K1
Ministral 8B (latest)Mistral$0.100$0.100128K1
Nova Micro (EU)amazon-bedrock$0.040$0.160128K1
GPT OSS 120Bsynthetic$0.100$0.100131K1
DeepSeek V4 Flash LatestDeepSeek$0.050$0.1601.31M4
GPT OSS 20Bcortecs$0.045$0.167131K1
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.039$0.1801M6

顯示前 60 項,共 1380 項。 用 完整目錄 進一步篩選。

Frequently asked questions

How many AI models support 工具呼叫?

1380 canonical models in our database currently support 工具呼叫. 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 工具呼叫?

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 工具呼叫 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 工具呼叫.

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 (89), Kimi K3 (75), DeepSeek V4 Pro (72).

How is 工具呼叫 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.

最近更新:

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.