Start free

Give your agent LLM API access to generate text, embeddings and more during calls.

Connect LLM API to your AgentCalls agent and it can draft replies, answer product or policy questions, and create embeddings for search, all during a live call. Your agent can also check which models are available and cancel a running batch job when plans change. Connect with your own credentials from the LLM API settings. Your agent works with the same account you already use, so usage stays under your control.

Start freeSee pricing

What your agent can do with LLM API

  • Answer caller questions by generating a complete text response from your own content
  • Create text embeddings to match a caller's question against your knowledge base
  • Check which AI models are available and their current capabilities before a call
  • Cancel an in-progress batch job when a request is no longer needed
  • Count input tokens before sending a longer request

LLM API exposes 12 actions. You choose which ones the agent may use and whether each runs during or after the call.

Example calls

Caller asks a detailed product question

  1. Caller

    Does your standard plan include priority support, and what's the response time?

  2. Agent

    Yes, the standard plan includes priority support with a response within four business hours. Would you like me to send you the full plan comparison by text?

  3. Caller

    Yes please, send it to this number.

  4. Agent

    Done. You'll get it in a moment. Anything else I can help with?

Matching a question to the help center

  1. Caller

    I need to change the delivery address on an order that hasn't shipped yet.

  2. Agent

    I can help with that. Changes are allowed until the order is packed, and I can find the matching steps in our help guide. Could you give me the order number?

  3. Caller

    It's 4815.

  4. Agent

    Thanks, Sarah. Order 4815 hasn't been packed yet, so the address can still be updated. I'll send you the steps now.

Outbound follow-up after a batch job

  1. Agent

    Hi, this is Maple Dental calling for James. Your sample batch of follow-up summaries is ready, and I'm calling to confirm you still want those sent this week.

  2. Caller

    Actually, hold off. We changed the campaign.

  3. Agent

    No problem. I've cancelled the batch job, so nothing else will be generated. Thanks for letting me know, James.

How to connect LLM API

  1. 1

    Create your agent

    Sign up to AgentCalls, pick an English or Arabic voice and write what the agent should know and do in plain language.

  2. 2

    Connect LLM API

    From Integrations in the dashboard, choose LLM API and enter the connection details from your LLM API account settings.

  3. 3

    Choose the actions

    In the agent editor, enable the LLM API actions the agent may use and set each to run during the call or afterwards. Then test it from your browser.

Related integrations

Perplexity AICustomer supportPerplexity AI provides conversational AI models for generating human-like text responsesSerpApiSpreadsheets & databasesSerpApi provides a real-time API for structured search engine results, allowing developers to scrape, parse, and…FirecrawlAI, search & researchFirecrawl automates web crawling and data extraction, enabling organizations to gather content, index sites, and gain…TavilyAI, search & researchTavily offers search and data retrieval solutions, helping teams quickly locate and filter relevant information from…ExaSpreadsheets & databasesExa focuses on data extraction and search, helping teams gather, analyze, and visualize information from websites…ElevenLabsAI, search & researchCreate natural AI voices instantly in any language - perfect for video creators, developers, and businesses.

All AI, search & research integrations

Questions, answered.

Does this work during the call or after it?

Both. Your agent can generate responses, create embeddings and check models while the caller is on the line. It can also act after the call, such as sending a follow-up summary.

What do I need to connect LLM API?

You need an LLM API account with its own credentials, created in the tool's settings. Then sign in to the AgentCalls dashboard and connect the tool to your agent.

Which plan includes this integration?

Tool integrations, including LLM API, are included from the Growth plan.

Page drafted from the tool's public description and reviewed automatically for accuracy of claims

Put your agent to work with LLM API.

Connect in minutes, test from your browser, go live on a number in the US, UK or Gulf. Free to start, no card needed.

Start freeSee pricing