Capacidade · 2026-06-29
Modelos de IA com suporte a Tool calling
Comparativo de modelos que suportam tool calling / function calling para agentes e fluxos automatizados.
O que é?
- Tool calling (também chamado function calling) permite ao LLM emitir uma requisição JSON estruturada para invocar funções externas — busca, execução de código, consultas a banco de dados, etc.
- O modelo retorna nome da função e argumentos em JSON; seu runtime executa e devolve o resultado como tool message.
Por que importa
- Sem tool calling, agentes dependem de parsear texto livre com expressões regulares frágeis.
- Tool calling é a chave para RAG, loops ReAct e assistentes multietapa funcionarem de forma confiável em produção.
745 modelos com esta capacidade
Mostrando os 60 primeiros de 745. Use o diretório completo para filtrar mais.
Frequently asked questions
How many AI models support tool calling?
745 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?
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 tool calling 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 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: Kimi K2.6 (49), Kimi K2.5 (48), GLM-5.1 (47).
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
- Voxtral Small 24B 2507$0.00 in / $0.00 out
- Ling-2.6-flash$0.01 in / $0.03 out
- Meta-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$0.02 in / $0.04 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
Vendors in this list
Última atualização:
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.