Возможность · 2026-11-13
ИИ-модели с поддержкой Tool calling
Сравнение моделей, поддерживающих tool calling / function calling для агентов и автоматизированных процессов.
Что это?
- Tool calling (он же function calling) позволяет LLM генерировать структурированный JSON-запрос для вызова внешних функций — поиск, выполнение кода, запросы к БД и т. д.
- Модель возвращает имя функции и аргументы в JSON; ваш runtime выполняет вызов и возвращает результат как tool message.
Зачем это важно
- Без tool calling агенты вынуждены парсить свободный текст хрупкими регулярными выражениями.
- Tool calling — ключ к надёжной работе RAG, циклов ReAct и многошаговых ассистентов в продакшене.
1511 моделей с этой возможностью
Показаны первые 60 из 1511. Перейдите к полному каталогу для дополнительной фильтрации.
Frequently asked questions
How many AI models support Tool Calling?
1511 canonical models in our database currently support Tool Calling. 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 Tool Calling?
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 Tool Calling 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 Tool Calling.
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 (93), GLM-5.3 (93), GLM-5.2 (90).
How is Tool Calling 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.
Explore more
Top models with this capability
- Qwen3.8 27B$0.00 in / $0.00 out
- Ambient Small$0.00 in / $0.00 out
- Llama-3.1-8B-Instruct$0.02 in / $0.03 out
- Meta Llama 3.1 8B Instruct Turbo$0.02 in / $0.03 out
- Mistral Nemo$0.03 in / $0.03 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
Vendors in this list
Последнее обновление:
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.