Search
K
OpenAI API

Create a thread and run it in one request.

post
https://api.openai.com/v1/threads/runs

Body

application/json

CreateThreadAndRunRequest

* Additional properties are NOT allowed.
assistant_idstringrequired

The ID of the assistant to use to execute this run.

threadobject

Options to create a new thread. If no thread is provided when running a
request, an empty thread will be created.

* Additional properties are NOT allowed.
Show Child Parameters
modelAny Of

The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

Example:gpt-4o

Variant 1string
instructionsstring | null

Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

toolsOne Of
array | null

Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

<= 20 items

Code interpreter toolobject
Show Child Parameters
tool_resourcesobject | null

A set of resources that are used by the assistant’s tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

Show Child Parameters
metadataobject | null

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 | null

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

Default:1

>= 0<= 2

Example:1

top_pnumber | null

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Default:1

>= 0<= 1

Example:1

streamboolean | null

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_tokensinteger | null

The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

>= 256

max_completion_tokensinteger | null

The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

>= 256

truncation_strategyobject

Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.

Show Child Parameters
tool_choiceOne Of
AssistantsApiToolChoiceOptionstring

none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

Allowed values:noneautorequired

parallel_tool_callsboolean

Whether to enable parallel function calling during tool use.

Default:true

response_formatOne Of
AssistantsApiResponseFormatOptionstring

auto is the default value

Allowed values:auto

Response

200 application/json

OK

A run on a thread

Represents an execution run on a thread.

idstringrequired

The identifier, which can be referenced in API endpoints.

objectstringrequired

The object type, which is always thread.run.

Allowed values:thread.run

created_atintegerrequired

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

thread_idstringrequired

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

assistant_idstringrequired

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

statusstringrequired

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

Allowed values:queuedin_progressrequires_actioncancellingcancelledfailedcompletedincompleteexpired

required_actionobject | nullrequired

Details on the action required to continue the run. Will be null if no action is required.

Show Child Parameters
last_errorobject | nullrequired

The last error associated with this run. Will be null if there are no errors.

Show Child Parameters
expires_atinteger | nullrequired

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

started_atinteger | nullrequired

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

cancelled_atinteger | nullrequired

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

failed_atinteger | nullrequired

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

completed_atinteger | nullrequired

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

incomplete_detailsobject | nullrequired

Details on why the run is incomplete. Will be null if the run is not incomplete.

Show Child Parameters
modelstringrequired

The model that the assistant used for this run.

instructionsstringrequired

The instructions that the assistant used for this run.

toolsOne Of
arrayrequired

The list of tools that the assistant used for this run.

Default:[]

<= 20 items

Code interpreter toolobject
Show Child Parameters
metadataobject | nullrequired

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.

usageobject | nullrequired

Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

Show Child Parameters
temperaturenumber | null

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

top_pnumber | null

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

max_prompt_tokensinteger | nullrequired

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

>= 256

max_completion_tokensinteger | nullrequired

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

>= 256

truncation_strategyobjectrequired

Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.

Show Child Parameters
tool_choiceOne Of
required
AssistantsApiToolChoiceOptionstring

none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

Allowed values:noneautorequired

parallel_tool_callsbooleanrequired

Whether to enable parallel function calling during tool use.

Default:true

response_formatOne Of
required
AssistantsApiResponseFormatOptionstring

auto is the default value

Allowed values:auto

post/threads/runs

Body

{ "assistant_id": "assistant_id" }
 
200 application/json

Retrieves a thread.

get
https://api.openai.com/v1/threads/{thread_id}

Path Parameters

thread_idstringrequired

The ID of the thread to retrieve.

Response

200 application/json

OK

Thread

Represents a thread that contains messages.

idstringrequired

The identifier, which can be referenced in API endpoints.

objectstringrequired

The object type, which is always thread.

Allowed values:thread

created_atintegerrequired

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

tool_resourcesobject | nullrequired

A set of resources that are made available to the assistant’s tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

Show Child Parameters
metadataobject | nullrequired

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.

get/threads/{thread_id}
 
200 application/json

Modifies a thread.

post
https://api.openai.com/v1/threads/{thread_id}

Path Parameters

thread_idstringrequired

The ID of the thread to modify. Only the metadata can be modified.

Body

application/json

ModifyThreadRequest

* Additional properties are NOT allowed.
tool_resourcesobject | null

A set of resources that are made available to the assistant’s tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

Show Child Parameters
metadataobject | null

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.

Response

200 application/json

OK

Thread

Represents a thread that contains messages.

idstringrequired

The identifier, which can be referenced in API endpoints.

objectstringrequired

The object type, which is always thread.

Allowed values:thread

created_atintegerrequired

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

tool_resourcesobject | nullrequired

A set of resources that are made available to the assistant’s tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

Show Child Parameters
metadataobject | nullrequired

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.

post/threads/{thread_id}

Body

{}
 
200 application/json

Delete a thread.

delete
https://api.openai.com/v1/threads/{thread_id}

Path Parameters

thread_idstringrequired

The ID of the thread to delete.

Response

200 application/json

OK

DeleteThreadResponse

idstringrequired
deletedbooleanrequired
objectstringrequired

Allowed values:thread.deleted

delete/threads/{thread_id}
 
200 application/json

Returns a list of messages for a given thread.

get
https://api.openai.com/v1/threads/{thread_id}/messages

Query Parameters

limitinteger

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

Default:20

orderstring

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

Allowed values:ascdesc

Default:desc

afterstring

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

beforestring

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

run_idstring

Filter messages by the run ID that generated them.

Path Parameters

thread_idstringrequired

The ID of the thread the messages belong to.

Response

200 application/json

OK

ListMessagesResponse

objectstringrequired

Example:list

dataarray[object]required

Represents a message within a thread.

Show Child Parameters
first_idstringrequired

Example:msg_abc123

last_idstringrequired

Example:msg_abc123

has_morebooleanrequired

Example:false

get/threads/{thread_id}/messages
 
200 application/json