Authorizations
Authentication header containing API key (find it in dashboard). The format is "Bearer YOUR_API_KEY"
Query Parameters
Limit the number of conversation flows returned. Default 1000, Max 1000. To retrieve more than 1000, use pagination_key to continue fetching the next page.
x <= 1000
The pagination key to continue fetching the next page of conversation flows. Pagination key is represented by a conversation flow id here, and it's exclusive (not included in the fetched conversation flows). The last conversation flow id from the list conversation flows is usually used as pagination key here. If not set, will start from the beginning.
Specifies the version of the conversation flow associated with the pagination_key. When paginating, both the pagination_key and its version must be provided to ensure consistent ordering and to fetch the next page correctly.
Response
Successfully retrieved conversation flows
Unique identifier for the conversation flow
Version number of the conversation flow
Global prompt used in every node of the conversation flow.
"You are a helpful customer service agent."
Tools available in the conversation flow.
[
{
"type": "custom",
"name": "get_customer_info",
"description": "Get customer information from database",
"tool_id": "tool_001",
"url": "https://api.example.com/customer",
"method": "GET"
}
]
ID of the start node in the conversation flow.
"start"
Controls the randomness of the model's responses. Lower values make responses more deterministic.
0 <= x <= 1
0.7
Whether to use strict mode for tool calls. Only applicable when using structured output models.
true
Default dynamic variables that can be referenced throughout the conversation flow.
{
"company_name": "Retell Inc",
"support_hours": "9 AM - 5 PM"
}
Knowledge base IDs for RAG (Retrieval-Augmented Generation).
["kb_001", "kb_002"]
Knowledge base configuration for RAG retrieval.
Display position for the begin tag in the frontend.
A list of MCP server configurations to use for this conversation flow.
Who starts the conversation - user or agent.
user
, agent
"agent"
The model choice for the conversation flow.
Array of nodes in the conversation flow.
[
{
"id": "start",
"type": "conversation",
"instruction": {
"type": "prompt",
"text": "Greet the customer and ask how you can help them."
},
"edges": [
{
"id": "edge_1",
"transition_condition": {
"type": "prompt",
"prompt": "Customer wants to book appointment"
},
"destination_node_id": "book_appointment"
}
]
}
]