realtimeResponse
RealtimeResponse Model
Represents the payload returned when initializing a real-time chat session with an assistant. It contains both assistant configuration details and chat-related metadata used for model execution.
assistant (object) Required
Configuration object representing the assistant participating in the real-time chat. This includes behavioral settings, retrieval strategies, UI elements, and token optimization policies.
- See full documentation: Assistant Model
chat_id (integer) Required
The unique identifier for the chat session that has just been created.
Used to reference or resume the session.
model (string) Required
The identifier for the model used in the response generation.
- Minimum length: 1 character
system_prompt (string) Required
A prompt used to instruct the assistant system-level behavior during this real-time session.
Should include contextual or behavioral instructions for the assistant.
- Minimum length: 1 character
Should include contextual or behavioral instructions for the assistant.
temperature (number) Required
Controls the randomness of the model's output.
- Range:
0to2 - Higher values increase creativity and variability in responses.
max_tokens (integer) Required
Defines the upper limit for the number of tokens that can be generated in a single response.
additional_params (object, Optional)
A dictionary of extra parameters passed to the model for custom behavior.
- Keys: Must be strings
- Values: Nullable strings
Example
{
"assistant": {
"id": 0,
"generation_config": "string",
"generation_config_pretools": "string",
"description": "string",
"system_prompt": "string",
"temperature": 2,
"max_responses": 2147483647,
"max_msg_length": 2147483647,
"initial_message": "string",
"end_message": "string",
"add_to_user_message": "string",
"max_consecutive_tool_calls": 2147483647,
"created_at": "2025-05-29T13:29:50.467Z",
"updated_at": "2025-05-29T13:29:50.467Z",
"retrieval_faq": 0,
"retrieval_fixed_faq": 0,
"retrieval_lessons": 0,
"matrix_mode_available": true,
"not_info_message": "string",
"strategy_to_optimize_tokens": "string",
"faq_available": true,
"fixed_available": true,
"lessons_available": true,
"realtime_available": true,
"info": "string",
"colors": {},
"logo": "string",
"streaming_available": true,
"tools": [
0
],
"pretools": [
0
]
},
"chat_id": 0,
"model": "string",
"system_prompt": "string",
"temperature": 0,
"max_tokens": 0,
"additional_params": {}
}