能力 · 2026-05-12
支持 Tool calling 的 AI 模型
对比支持工具调用 / 函数调用的 AI 模型 —— 适合搭建 Agent 与自动化流程。
这是什么？
- Tool calling（也叫 function calling）让 LLM 以结构化 JSON 发出请求，调用你暴露的外部函数 —— 搜索、代码执行、数据库查询等。
- 模型返回函数名与参数 JSON；你的运行时执行后，再把结果以 tool message 喂回模型。
为什么重要
- 没有 tool calling 时，Agent 往往只能靠脆弱的正则去解析自由文本。
- Tool calling 是让 RAG、ReAct 循环与多步助手在生产环境可靠运行的关键。
660 个模型支持此能力
显示前 60 / 共 660 项。 用 完整目录 进一步筛选。
Frequently asked questions
How many AI models support 工具调用?
660 canonical models in our database currently support 工具调用. The list is regenerated on every data refresh, so it always reflects the latest model releases from models.dev.
What is the cheapest model with 工具调用?
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 工具调用 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 工具调用.
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: Kimi K2.5 (45), MiniMax-M2.5 (40), GLM-5 (38).
How is 工具调用 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 pulls models.dev once a day, regenerates the canonical model list, and rebuilds these pages so newly released models appear within 24 hours.
Explore more
Top models with this capability
- Voxtral Small 24B 2507$0.00 in / $0.00 out
- Meta-Llama-3.1-8B-Instruct$0.02 in / $0.03 out
- Llama 3.1 8B Turbo$0.02 in / $0.03 out
- Mistral Nemo Instruct 2407$0.02 in / $0.04 out
- Hermes 4 14B$0.01 in / $0.05 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
最近更新：
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.