Create a run for a thread
Create a run for a thread.
Authorizations
Tune API Keys are the preferred way to authenticate with the API. You can create an API Key from your Tune Studio Profile → 'Access Keys' (in sidebar)
Body
The ID of the assistant to use to execute this run. (not supported yet).
The ID of the Model to be used to execute this run. (required).
Used as system prompt. Overrides the assistant instruction. If provided, the assistant will use this prompt instead of the one associated with the assistant.
Adds additional instructions at the end of the instructions for the run.
Tools to be used for this run. If provided, the assistant will use these tools instead of the ones associated with the assistant.
Metadata to store additional information in key-value pairs.
Will be used to control the randomness of the output. The higher the temperature, the more random the output. The lower the temperature, the more deterministic the output.
The probability mass model will consider to generate the output. 0.1 means only the top 10% of the tokens will be considered.
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.
The maximum number of tokens to generate in a single prompt. This is useful for limiting the length of the output.
The maximum number of tokens to generate in a single completion. This is useful for limiting the length of the output.
Response
The ID of the run.
"run".
The time the run was created.
The ID of the thread.
queued, in_progress, requires_action, cancelling, cancelled, failed, completed, or expired..
The time the run expires.
The time the run started.
The time the run was cancelled.
The time the run was completed.
The time the run failed.
The model used for the run.
The instructions for the run.
The tools used in the run.
The file IDs used in the run.
The metadata for the run.
Was this page helpful?