max_tool_calls
parameter.store=false
.client.responses.create
method. For a complete example, see the getting started notebook.
previous_response_id
previous_response_id
parameter. This tells the API to use the context from a previous response, so you don’t have to send the entire conversation history again. For a complete example, see the previous response ID notebook.
previous_response_id
store=False
store=False
. If you do this, you will not be able to use the previous_response_id
to continue the conversation. For a complete example, see the store=False notebook.
store=True
), you can immediately delete them from storage using the DELETE endpoint. This permanently removes the conversation data.
id
: Unique identifier for the response (e.g., resp_abc123...
)created_at
: Unix timestamp when the response was createdstatus
: Status of the response (typically "completed"
)model
: The model used to generate the responseoutput
: Array of message objects, tool calls, and tool outputsusage
: Token usage information:
prompt_tokens
: Number of tokens in the promptcompletion_tokens
: Number of tokens in the completiontotal_tokens
: Total tokens usedprevious_response_id
: ID of the previous response in the conversation (if any)store
: Whether the response was stored (boolean)max_tool_calls
: Maximum number of tool calls allowed (if set)