قدرة · 2026-08-13
نماذج ذكاء اصطناعي تدعم Tool calling
مقارنة النماذج التي تدعم استدعاء الأدوات / استدعاء الدوال لبناء وكلاء وتدفقات مؤتمتة.
ما هذا؟
- يتيح Tool calling (المعروف أيضًا بـ function calling) للنموذج إصدار طلب JSON منظّم لاستدعاء دوال خارجية — بحث، تنفيذ كود، استعلامات قواعد بيانات، إلخ.
- يُعيد النموذج اسم الدالة والمعاملات بصيغة JSON؛ يقوم وقت التشغيل لديك بتنفيذها وإرجاع النتيجة كرسالة أداة.
لماذا يهم
- بدون tool calling، يضطر الوكلاء لتحليل نص حر باستخدام تعبيرات نمطية هشّة.
- Tool calling هو المفتاح لتشغيل RAG وحلقات ReAct والمساعدين متعددي الخطوات بشكل موثوق في الإنتاج.
981 نماذج تدعم هذه القدرة
عرض أول 60 من إجمالي 981. استخدم الفهرس الكامل لمزيد من التصفية.
Frequently asked questions
How many AI models support استدعاء الأدوات?
981 canonical models in our database currently support استدعاء الأدوات. 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 استدعاء الأدوات?
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 استدعاء الأدوات 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 استدعاء الأدوات.
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 استدعاء الأدوات 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
- Llama 3.1 8B Instruct$0.02 in / $0.03 out
- Mistral Nemo Instruct 2407$0.02 in / $0.03 out
- Meta Llama 3.1 8B Instruct Turbo$0.02 in / $0.03 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
Vendors in this list
آخر تحديث:
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.