Create Retell LLM

POST

create-retell-llm

import Retell from 'retell-sdk';

const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
});

async function main() {
  const llmResponse = await client.llm.create();

  console.log(llmResponse.llm_id);
}

main();

{
  "llm_id": "oBeDLoLOeuAbiuaMFXRtDOLriTJ5tSxD",
  "model": "gpt-4o",
  "s2s_model": "gpt-4o-realtime",
  "model_temperature": 0,
  "model_high_priority": true,
  "tool_call_strict_mode": true,
  "general_prompt": "You are ...",
  "general_tools": [
    {
      "type": "end_call",
      "name": "end_call",
      "description": "End the call with user."
    }
  ],
  "states": [
    {
      "name": "information_collection",
      "state_prompt": "You will follow the steps below to collect information...",
      "edges": [
        {
          "destination_state_name": "appointment_booking",
          "description": "Transition to book an appointment."
        }
      ],
      "tools": [
        {
          "type": "transfer_call",
          "name": "transfer_to_support",
          "description": "Transfer to the support team.",
          "number": "16175551212"
        }
      ]
    },
    {
      "name": "appointment_booking",
      "state_prompt": "You will follow the steps below to book an appointment...",
      "tools": [
        {
          "type": "book_appointment_cal",
          "name": "book_appointment",
          "description": "Book an annual check up.",
          "cal_api_key": "cal_live_xxxxxxxxxxxx",
          "event_type_id": 60444,
          "timezone": "America/Los_Angeles"
        }
      ]
    }
  ],
  "starting_state": "information_collection",
  "begin_message": "Hey I am a virtual assistant calling from Retell Hospital.",
  "default_dynamic_variables": {
    "customer_name": "John Doe"
  },
  "knowledge_base_ids": [
    "<string>"
  ],
  "last_modification_timestamp": 1703413636133
}

Authorizations

Authorization

string

header

required

Authentication header containing API key (find it in dashboard). The format is "Bearer YOUR_API_KEY"

Body

application/json

model

enum<string> | null

Select the underlying text LLM. If not set, would default to gpt-4o.

Available options:

gpt-4o,

gpt-4o-mini,

claude-3.7-sonnet,

claude-3.5-haiku

Example:

"gpt-4o"

s2s_model

enum<string> | null

Select the underlying speech to speech model. Can only set this or model, not both.

Available options:

gpt-4o-realtime,

gpt-4o-mini-realtime

Example:

"gpt-4o-realtime"

model_temperature

number

If set, will control the randomness of the response. Value ranging from [0,1]. Lower value means more deterministic, while higher value means more random. If unset, default value 0 will apply. Note that for tool calling, a lower value is recommended.

Example:

0

model_high_priority

boolean

If set to true, will use high priority pool with more dedicated resource to ensure lower and more consistent latency, default to false. This feature usually comes with a higher cost.

Example:

true

tool_call_strict_mode

boolean

Only applicable when model is gpt-4o or gpt-4o mini. If set to true, will use structured output to make sure tool call arguments follow the json schema. The time to save a new tool or change to a tool will be longer as additional processing is needed. Default to false.

Example:

true

general_prompt

string | null

General prompt appended to system prompt no matter what state the agent is in.

System prompt (with state) = general prompt + state prompt.
System prompt (no state) = general prompt.

Example:

"You are ..."

general_tools

object[] | null

A list of tools the model may call (to get external knowledge, call API, etc). You can select from some common predefined tools like end call, transfer call, etc; or you can create your own custom tool (last option) for the LLM to use.

Tools of LLM (with state) = general tools + state tools + state transitions
Tools of LLM (no state) = general tools

Example:

[
  {
    "type": "end_call",
    "name": "end_call",
    "description": "End the call with user."
  }
]

states

object[] | null

States of the LLM. This is to help reduce prompt length and tool choices when the call can be broken into distinct states. With shorter prompts and less tools, the LLM can better focus and follow the rules, minimizing hallucination. If this field is not set, the agent would only have general prompt and general tools (essentially one state).

states.name

string

required

Name of the state, must be unique for each state. Must be consisted of a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64 (no space allowed).

Example:

"information_collection"

states.state_prompt

string

Prompt of the state, will be appended to the system prompt of LLM.

System prompt = general prompt + state prompt.

Example:

"## Task\nYou will follow the steps below..."

states.edges

object[]

Edges of the state define how and what state can be reached from this state.

states.tools

object[]

A list of tools specific to this state the model may call (to get external knowledge, call API, etc). You can select from some common predefined tools like end call, transfer call, etc; or you can create your own custom tool (last option) for the LLM to use.

Tools of LLM = general tools + state tools + state transitions

Example:

[
  {
    "name": "information_collection",
    "state_prompt": "You will follow the steps below to collect information...",
    "edges": [
      {
        "destination_state_name": "appointment_booking",
        "description": "Transition to book an appointment."
      }
    ],
    "tools": [
      {
        "type": "transfer_call",
        "name": "transfer_to_support",
        "description": "Transfer to the support team.",
        "number": "16175551212"
      }
    ]
  },
  {
    "name": "appointment_booking",
    "state_prompt": "You will follow the steps below to book an appointment...",
    "tools": [
      {
        "type": "book_appointment_cal",
        "name": "book_appointment",
        "description": "Book an annual check up.",
        "cal_api_key": "cal_live_xxxxxxxxxxxx",
        "event_type_id": 60444,
        "timezone": "America/Los_Angeles"
      }
    ]
  }
]

starting_state

string | null

Name of the starting state. Required if states is not empty.

Example:

"information_collection"

begin_message

string | null

First utterance said by the agent in the call. If not set, LLM will dynamically generate a message. If set to "", agent will wait for user to speak first.

Example:

"Hey I am a virtual assistant calling from Retell Hospital."

default_dynamic_variables

object | null

Default dynamic variables represented as key-value pairs of strings. These are injected into your Retell LLM prompt and tool description when specific values are not provided in a request. Only applicable for Retell LLM.

Example:

{ "customer_name": "John Doe" }

knowledge_base_ids

string[] | null

A list of knowledge base ids to use for this resource. Set to null to remove all knowledge bases.

Response

201

application/json

Successfully created a new Retell LLM Response Engine.

llm_id

string

required

Unique id of Retell LLM Response Engine.

Example:

"oBeDLoLOeuAbiuaMFXRtDOLriTJ5tSxD"

last_modification_timestamp

integer

required

Last modification timestamp (milliseconds since epoch). Either the time of last update or creation if no updates available.

Example:

1703413636133

model

enum<string> | null

Select the underlying text LLM. If not set, would default to gpt-4o.

Available options:

gpt-4o,

gpt-4o-mini,

claude-3.7-sonnet,

claude-3.5-haiku

Example:

"gpt-4o"

s2s_model

enum<string> | null

Select the underlying speech to speech model. Can only set this or model, not both.

Available options:

gpt-4o-realtime,

gpt-4o-mini-realtime

Example:

"gpt-4o-realtime"

model_temperature

number

Example:

0

model_high_priority

boolean

If set to true, will use high priority pool with more dedicated resource to ensure lower and more consistent latency, default to false. This feature usually comes with a higher cost.

Example:

true

tool_call_strict_mode

boolean

Example:

true

general_prompt

string | null

General prompt appended to system prompt no matter what state the agent is in.

System prompt (with state) = general prompt + state prompt.
System prompt (no state) = general prompt.

Example:

"You are ..."

general_tools

object[] | null

Tools of LLM (with state) = general tools + state tools + state transitions
Tools of LLM (no state) = general tools

Example:

[
  {
    "type": "end_call",
    "name": "end_call",
    "description": "End the call with user."
  }
]

states

object[] | null

states.name

string

required

Name of the state, must be unique for each state. Must be consisted of a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64 (no space allowed).

Example:

"information_collection"

states.state_prompt

string

Prompt of the state, will be appended to the system prompt of LLM.

System prompt = general prompt + state prompt.

Example:

"## Task\nYou will follow the steps below..."

states.edges

object[]

Edges of the state define how and what state can be reached from this state.

states.tools

object[]

Tools of LLM = general tools + state tools + state transitions

Example:

[
  {
    "name": "information_collection",
    "state_prompt": "You will follow the steps below to collect information...",
    "edges": [
      {
        "destination_state_name": "appointment_booking",
        "description": "Transition to book an appointment."
      }
    ],
    "tools": [
      {
        "type": "transfer_call",
        "name": "transfer_to_support",
        "description": "Transfer to the support team.",
        "number": "16175551212"
      }
    ]
  },
  {
    "name": "appointment_booking",
    "state_prompt": "You will follow the steps below to book an appointment...",
    "tools": [
      {
        "type": "book_appointment_cal",
        "name": "book_appointment",
        "description": "Book an annual check up.",
        "cal_api_key": "cal_live_xxxxxxxxxxxx",
        "event_type_id": 60444,
        "timezone": "America/Los_Angeles"
      }
    ]
  }
]

starting_state

string | null

Name of the starting state. Required if states is not empty.

Example:

"information_collection"

begin_message

string | null

First utterance said by the agent in the call. If not set, LLM will dynamically generate a message. If set to "", agent will wait for user to speak first.

Example:

"Hey I am a virtual assistant calling from Retell Hospital."

default_dynamic_variables

object | null

Example:

{ "customer_name": "John Doe" }

knowledge_base_ids

string[] | null

A list of knowledge base ids to use for this resource. Set to null to remove all knowledge bases.

Was this page helpful?

Delete Agent Get Retell LLM

import Retell from 'retell-sdk';

const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
});

async function main() {
  const llmResponse = await client.llm.create();

  console.log(llmResponse.llm_id);
}

main();

{
  "llm_id": "oBeDLoLOeuAbiuaMFXRtDOLriTJ5tSxD",
  "model": "gpt-4o",
  "s2s_model": "gpt-4o-realtime",
  "model_temperature": 0,
  "model_high_priority": true,
  "tool_call_strict_mode": true,
  "general_prompt": "You are ...",
  "general_tools": [
    {
      "type": "end_call",
      "name": "end_call",
      "description": "End the call with user."
    }
  ],
  "states": [
    {
      "name": "information_collection",
      "state_prompt": "You will follow the steps below to collect information...",
      "edges": [
        {
          "destination_state_name": "appointment_booking",
          "description": "Transition to book an appointment."
        }
      ],
      "tools": [
        {
          "type": "transfer_call",
          "name": "transfer_to_support",
          "description": "Transfer to the support team.",
          "number": "16175551212"
        }
      ]
    },
    {
      "name": "appointment_booking",
      "state_prompt": "You will follow the steps below to book an appointment...",
      "tools": [
        {
          "type": "book_appointment_cal",
          "name": "book_appointment",
          "description": "Book an annual check up.",
          "cal_api_key": "cal_live_xxxxxxxxxxxx",
          "event_type_id": 60444,
          "timezone": "America/Los_Angeles"
        }
      ]
    }
  ],
  "starting_state": "information_collection",
  "begin_message": "Hey I am a virtual assistant calling from Retell Hospital.",
  "default_dynamic_variables": {
    "customer_name": "John Doe"
  },
  "knowledge_base_ids": [
    "<string>"
  ],
  "last_modification_timestamp": 1703413636133
}

Call (V2)

Phone Number

Agent

Single / Multi Prompt Response (Retell LLM)

Knowledge Base

Voice

Batch call

Account

Custom Telephony

Custom LLM

Authorizations

Body

Response