i am using the same assistant with squad of agents and how it's being cheapest like 10 cents difference https://cdn.discordapp.com/attachments/1465125593547931721/1465125593761710110/image.png?ex=6977f80a&is=6976a68a&hm=bd114e3fab0f9f0f239525d0ad0d4eea941fce00274ce4da24e599a592417a81& https://cdn.discordapp.com/attachments/1465125593547931721/1465125594068156478/image.png?ex=6977f80a&is=6976a68a&hm=15788199f9f9d5857f1de134aebe40bf68df8b55307e953eb527624f5afaaf58&

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

Why is the same assistant cheaper in squad mode? When you use a squad, each assistant is focused on a specific task, which reduces the amount of context and tokens processed per request. This leads to lower costs compared to running a single, all-in-one assistant, which consumes more tokens due to longer prompts and broader context. Tip: To optimize costs, keep each assistant's role focused and minimize squad size where possible. Reference: See the squads documentation for best practices on cost efficiency. Source: - [Squads Documentation](https://docs.vapi.ai/squads)

Hi there, The cost difference you're seeing when using squads vs a standalone assistant comes down to token optimization. Why Squads Can Be Cheaper: When you use a squad of specialized assistants instead of one large all-in-one assistant: 1. Shorter prompts per interaction - Each squad member has a focused system prompt with specific goals (1-3 tasks maximum), rather than one massive prompt covering everything 2. Fewer tokens per request - Shorter prompts consume fewer tokens each time the LLM processes a message 3. Only necessary tools loaded - Each assistant only has the tools it needs for its specific task, reducing context size How This Saves Money: The majority of LLM costs come from: • Input tokens (your system prompt + conversation history) • Output tokens (assistant responses) With squads, each specialized assistant processes requests with a smaller context, so you're paying for fewer tokens overall even though you're technically using "multiple assistants." Example: Instead of one assistant with a 2,000-token prompt handling everything, you might have: • Triage assistant: 500 tokens • Scheduler assistant: 400 tokens • Support assistant: 600 tokens Each interaction only uses the prompt for the active assistant, not all prompts combined. You can check the detailed cost breakdown per call using our REST API: [https://docs.vapi.ai/api-reference/calls/get#response.body.costs](https://docs.vapi.ai/api-reference/calls/get#response.body.costs) Let me know if you have any other questions! Regards Vapi Support