🔄 Runs

Official Documentation

⋙ Create Thread and Run

Create a thread and run it in one request.

assistant_id string: The ID of the assistant to use to execute this run.
thread object: A thread object to create with the run.
model string: The ID of the Model to be used to execute this run.
instructions string: Override the default system message of the assistant.
tools array: Override the tools the assistant can use for this run.
tool_resources object or null: A set of resources that are used by the assistant's tools.
metadata object: Set of 16 key-value pairs that can be attached to an object.
temperature number: What sampling temperature to use, between 0 and 2.
top_p number or null: An alternative to sampling with temperature.
stream boolean: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.
max_prompt_tokens integer: The maximum number of prompt tokens that may be used over the course of the run.
max_completion_tokens integer: The maximum number of completion tokens that may be used over the course of the run.
truncation_strategy object: @property {string} type - The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.; @property {integer} [last_messages] - The number of most recent messages from the thread when constructing the context for the run.
tool_choice string | object: Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like {"type": "TOOL_TYPE"} forces the model to call that tool.
parallel_tool_calls boolean: Whether to enable parallel function calling during tool use.
response_format string | object: Specifies the format that the model must output.

⋙ List Runs

Returns a list of runs belonging to a thread.

thread_id string: The ID of the thread the run belongs to.
limit integer: A limit on the number of objects to be returned.
order string: Sort order by the created_at timestamp of the objects.
after string: A cursor for use in pagination.
before string: A cursor for use in pagination.

⋙ Create Run

Create a run.

thread_id string: The ID of the thread to run.
include array: A list of additional fields to include in the response.
assistant_id string: The ID of the assistant to use to execute this run.
model string: The ID of the Model to be used to execute this run.
instructions string: Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.
additional_instructions string: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.
additional_messages array: Adds additional messages to the thread before creating the run.
tools array: Override the tools the assistant can use for this run.
metadata object: Set of 16 key-value pairs that can be attached to an object.
temperature number: What sampling temperature to use, between 0 and 2.
top_p number: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
stream boolean: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.
max_prompt_tokens integer: The maximum number of prompt tokens that may be used over the course of the run.
max_completion_tokens integer: The maximum number of completion tokens that may be used over the course of the run.
truncation_strategy object: Controls for how a thread will be truncated prior to the run.
tool_choice string or object: Controls for how a thread will be truncated prior to the run.
parallel_tool_calls boolean: Whether to enable parallel function calling during tool use.
response_format string or object: Specifies the format that the model must output.

⋙ Retrieve Run

Retrieves a run.

thread_id string: The ID of the thread that was run.
run_id string: The ID of the run to retrieve.

⋙ Modify Run

Modifies a run.

thread_id string: The ID of the thread that was run.
run_id string: The ID of the run to modify.
metadata object: Set of 16 key-value pairs that can be attached to an object.

⋙ Submit Tool Outputs to Run

When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

thread_id string: The ID of the thread to which this run belongs.
run_id string: The ID of the run that requires the tool output submission.
tool_outputs array: A list of tools for which the outputs are being submitted.
stream boolean: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

⋙ Cancel Run

Cancels a run that is `in_progress`.

thread_id string: The ID of the thread to which this run belongs.
run_id string: The ID of the run to cancel.

⋙ List Run Steps

Returns a list of run steps belonging to a run.

thread_id string: The ID of the thread the run and run steps belong to.
run_id string: The ID of the run the run steps belong to.
limit integer: A limit on the number of objects to be returned.
order string: Sort order by the created_at timestamp of the objects.
after string: A cursor for use in pagination.
before string: A cursor for use in pagination.
include array: A list of additional fields to include in the response.

⋙ Retrieve Run Step

Retrieves a run step.

thread_id string: The ID of the thread to which the run and run step belongs.
run_id string: The ID of the run to which the run step belongs.
step_id string: The ID of the run step to retrieve.
include array: A list of additional fields to include in the response.

⋙ Create Thread and Run

msg.payload Properties

⋙ List Runs

msg.payload Properties

⋙ Create Run

msg.payload Properties

⋙ Retrieve Run

msg.payload Properties

⋙ Modify Run

msg.payload Properties

⋙ Submit Tool Outputs to Run

msg.payload Properties

⋙ Cancel Run

msg.payload Properties

⋙ List Run Steps

msg.payload Properties

⋙ Retrieve Run Step

msg.payload Properties