v32

latestOpenAPI 3.1.0MITraw.githubusercontent.com2026-07-312881,4162.7 MB
Assistants

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.

post/threads/{thread_id}/runs/{run_id}/submit_tool_outputs

Path parameters

thread_idstring required

The ID of the thread to which this run belongs.

run_idstring required

The ID of the run that requires the tool output submission.

Request body

streamboolean nullable

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.

Response

OK

idstring required

The identifier, which can be referenced in API endpoints.

object'thread.run' required

The object type, which is always thread.run.

created_atinteger required

The Unix timestamp (in seconds) for when the run was created.

thread_idstring required

The ID of the thread that was executed on as a part of this run.

assistant_idstring required

The ID of the assistant used for execution of this run.

status'queued' | 'in_progress' | 'requires_action' | 'cancelling' | 'cancelled' | 'failed' | 'completed' | 'incomplete' | 'expired' required

The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

expires_atinteger nullable required

The Unix timestamp (in seconds) for when the run will expire.

started_atinteger nullable required

The Unix timestamp (in seconds) for when the run was started.

cancelled_atinteger nullable required

The Unix timestamp (in seconds) for when the run was cancelled.

failed_atinteger nullable required

The Unix timestamp (in seconds) for when the run failed.

completed_atinteger nullable required

The Unix timestamp (in seconds) for when the run was completed.

modelstring required

The model that the assistant used for this run.

instructionsstring required

The instructions that the assistant used for this run.

metadataMetadata nullable required

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

temperaturenumber nullable

The sampling temperature used for this run. If not set, defaults to 1.

top_pnumber nullable

The nucleus sampling value used for this run. If not set, defaults to 1.

max_prompt_tokensinteger nullable required

The maximum number of prompt tokens specified to have been used over the course of the run.

max_completion_tokensinteger nullable required

The maximum number of completion tokens specified to have been used over the course of the run.

parallel_tool_callsboolean required

Whether to enable parallel function calling during tool use.