Docs/API Reference/Request Parameters

Request Parameters

Complete reference for all request parameters available in the Responses API.

#Required Parameters

Parameter	Type	Description
model	string	Required. The model ID to use (e.g., "alphagent-smart").
input	string \| array	Required. The input prompt or conversation messages.

#Optional Parameters

Parameter	Type	Description
stream	boolean	Enable SSE streaming. Default: `false`
instructions	string	Custom system prompt for the model.
max_output_tokens	integer	Maximum tokens in the response.
temperature	number	Sampling temperature (0-2). Lower = more focused.

#Input Formats

The input parameter accepts two formats:

String Input

Simple string for single-turn queries.

Python

response = client.responses.create(
    model="alphagent-smart",
    input="What is AAPL trading at?"
)

Message Array Input

Array of messages for multi-turn conversations.

Python

response = client.responses.create(
    model="alphagent-smart",
    input=[
        {"role": "user", "content": "What is AAPL trading at?"},
        {"role": "assistant", "content": "AAPL is trading at $187.12."},
        {"role": "user", "content": "How does that compare to last week?"}
    ]
)

#Custom Instructions

Use the instructions parameter to provide custom system prompts.

Python

response = client.responses.create(
    model="alphagent-smart",
    input="Analyze TSLA",
    instructions="You are a conservative value investor. Focus on fundamentals and avoid speculation."
)

Models

Response Format