OpenAI API | Beta › Threads › Create Thread And Run

post/assistants

Create an assistant with a model and instructions.

Delete Assistant ->

AssistantDeleted

delete/assistants/{assistant_id}

Delete an assistant.

List Assistants -> CursorPage<

get/assistants

Returns a list of assistants.

Retrieve Assistant ->

get/assistants/{assistant_id}

Retrieves an assistant.

Modify Assistant ->

post/assistants/{assistant_id}

Modifies an assistant.

Domain types

Assistant = { id, created_at, description, 10 more... }

AssistantDeleted = { id, deleted, object }

AssistantStreamEvent = { data, event, enabled } | { data, event } | { data, event } | 21 more...

AssistantTool =

CodeInterpreterTool

FileSearchTool

FunctionTool

CodeInterpreterTool = { type }

FileSearchTool = { type, file_search }

FunctionTool = { function, type }

MessageStreamEvent = { data, event } | { data, event } | { data, event } | 2 more...

RunStepStreamEvent = { data, event } | { data, event } | { data, event } | 4 more...

RunStreamEvent = { data, event } | { data, event } | { data, event } | 7 more...

ThreadStreamEvent = { data, event, enabled }

Beta

Threads

beta.threads

Methods

Create Thread ->

post/threads

Create a thread.

Security

Bearer Auth

Example: Authorization: Bearer My API Key

Body parameters

messages?: Array<{ content, role, attachments, 1 more... }>

A list of messages to start the thread with.

metadata?: unknown

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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.

tool_resources?: { code_interpreter, file_search }

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.

Response fields

Request example

curl https://api.openai.com/v1/threads \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY"

200Example

{
  "id": "id",
  "created_at": 0,
  "metadata": {},
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Create Thread And Run ->

AssistantResponseFormatOption

post/threads/runs

Create a thread and run it in one request.

Security

Bearer Auth

Example: Authorization: Bearer My API Key

Body parameters

assistant_id: string

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

instructions?: string

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

max_completion_tokens?: number

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.

max_prompt_tokens?: number

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.

metadata?: unknown

model?: string |

ChatModel

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.

parallel_tool_calls?: boolean

Whether to enable parallel function calling during tool use.

response_format?:

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

stream?: false

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.

temperature?: number

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.

thread?: { messages, metadata, tool_resources }

If no thread is provided, an empty thread will be created.

tool_choice?:

AssistantToolChoiceOption

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 one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

tool_resources?: { code_interpreter, file_search }

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.

tools?: Array<

CodeInterpreterTool

FileSearchTool

FunctionTool

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

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. 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.

truncation_strategy?: { type, last_messages }

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

Response fields

Request example

curl https://api.openai.com/v1/threads/runs \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
      "assistant_id": "assistant_id",
      "model": "gpt-4o",
      "temperature": 1,
      "top_p": 1
    }'

200Example

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {},
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Delete Thread ->

ThreadDeleted

delete/threads/{thread_id}

Delete a thread.

Retrieve Thread ->

get/threads/{thread_id}

Retrieves a thread.

Modify Thread ->

post/threads/{thread_id}

Modifies a thread.

Domain types

AssistantResponseFormatOption = "auto" |

ResponseFormatText

ResponseFormatJSONObject

| 1 more...

AssistantToolChoice = { type, function }

AssistantToolChoiceFunction = { name }

AssistantToolChoiceOption = "none" | "auto" | "required" |

AssistantToolChoice

Thread = { id, created_at, metadata, 2 more... }

ThreadDeleted = { id, deleted, object }

Beta Threads

Messages

beta.threads.messages

Methods

Create Message ->

post/threads/{thread_id}/messages

Create a message.

Delete Message ->

MessageDeleted

delete/threads/{thread_id}/messages/{message_id}

Deletes a message.

List Messages -> CursorPage<

get/threads/{thread_id}/messages

Returns a list of messages for a given thread.

Retrieve Message ->

get/threads/{thread_id}/messages/{message_id}

Retrieve a message.

Modify Message ->

FileCitationDeltaAnnotation

post/threads/{thread_id}/messages/{message_id}

Modifies a message.

Domain types

Annotation =

FileCitationAnnotation

FilePathAnnotation

AnnotationDelta =

FilePathDeltaAnnotation

FileCitationAnnotation = { end_index, file_citation, start_index, 2 more... }

FileCitationDeltaAnnotation = { index, type, end_index, 3 more... }

FilePathAnnotation = { end_index, file_path, start_index, 2 more... }

FilePathDeltaAnnotation = { index, type, end_index, 3 more... }

ImageFile = { file_id, detail }

ImageFileContentBlock = { image_file, type }

ImageFileDelta = { detail, file_id }

ImageFileDeltaBlock = { index, type, image_file }

ImageURL = { url, detail }

ImageURLContentBlock = { image_url, type }

ImageURLDelta = { detail, url }

ImageURLDeltaBlock = { index, type, image_url }

Message = { id, assistant_id, attachments, 11 more... }

MessageContent =

ImageFileContentBlock

ImageURLContentBlock

TextContentBlock

| 1 more...

MessageContentDelta =

ImageFileDeltaBlock

TextDeltaBlock

RefusalDeltaBlock

| 1 more...

MessageContentPartParam =

ImageFileContentBlock

ImageURLContentBlock

TextContentBlockParam

MessageDeleted = { id, deleted, object }

MessageDelta = { content, role }

MessageDeltaEvent = { id, delta, object }

RefusalContentBlock = { refusal, type }

RefusalDeltaBlock = { index, type, refusal }

Text = { annotations, value }

TextContentBlock = { text, type }

TextContentBlockParam = { text, type }

TextDelta = { annotations, value }

TextDeltaBlock = { index, type, text }

Beta Threads

Runs

beta.threads.runs

Methods

Cancel A Run ->

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

Cancels a run that is in_progress.

Create Run ->

post/threads/{thread_id}/runs

Create a run.

List Runs -> CursorPage<

get/threads/{thread_id}/runs

Returns a list of runs belonging to a thread.

Retrieve Run ->

get/threads/{thread_id}/runs/{run_id}

Retrieves a run.

Submit Tool Outputs To Run ->

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

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.

Modify Run ->

CodeInterpreterToolCallDelta

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

Modifies a run.

Domain types

RequiredActionFunctionToolCall = { id, function, type }

Run = { id, assistant_id, cancelled_at, 24 more... }

RunStatus = "queued" | "in_progress" | "requires_action" | 6 more...

Beta Threads Runs

Steps

beta.threads.runs.steps

Methods

List Run Steps -> CursorPage<

RunStep

get/threads/{thread_id}/runs/{run_id}/steps

Returns a list of run steps belonging to a run.

Retrieve Run Step ->

RunStep

get/threads/{thread_id}/runs/{run_id}/steps/{step_id}

Retrieves a run step.

Domain types

CodeInterpreterLogs = { index, type, logs }

CodeInterpreterOutputImage = { index, type, image }

CodeInterpreterToolCall = { id, code_interpreter, type }

CodeInterpreterToolCallDelta = { index, type, id, 1 more... }

FileSearchToolCall = { id, file_search, type }

FileSearchToolCallDelta = { file_search, index, type, 1 more... }

FunctionToolCall = { id, function, type }

FunctionToolCallDelta = { index, type, id, 1 more... }

MessageCreationStepDetails = { message_creation, type }

RunStep = { id, assistant_id, cancelled_at, 13 more... }

RunStepDelta = { step_details }

RunStepDeltaEvent = { id, delta, object }

RunStepDeltaMessageDelta = { type, message_creation }

RunStepInclude = "step_details.tool_calls[*].file_search.results[*].content"

ToolCall =

CodeInterpreterToolCall

FileSearchToolCall

FunctionToolCall

ToolCallDelta =

FileSearchToolCallDelta

FunctionToolCallDelta

ToolCallDeltaObject = { type, tool_calls }

ToolCallsStepDetails = { tool_calls, type }

Beta

Vector Stores

beta.vector_stores

Methods

Create Vector Store ->

post/vector_stores

Create a vector store.

Delete Vector Store ->

VectorStoreDeleted

delete/vector_stores/{vector_store_id}

Delete a vector store.

List Vector Stores -> CursorPage<

get/vector_stores

Returns a list of vector stores.

Retrieve Vector Store ->

get/vector_stores/{vector_store_id}

Retrieves a vector store.

Modify Vector Store ->

StaticFileChunkingStrategyObject

post/vector_stores/{vector_store_id}

Modifies a vector store.

Domain types

AutoFileChunkingStrategyParam = { type }

FileChunkingStrategy =

OtherFileChunkingStrategyObject

FileChunkingStrategyParam =

AutoFileChunkingStrategyParam

StaticFileChunkingStrategyParam

OtherFileChunkingStrategyObject = { type }

StaticFileChunkingStrategy = { chunk_overlap_tokens, max_chunk_size_tokens }

StaticFileChunkingStrategyObject = { static, type }

StaticFileChunkingStrategyParam = { static, type }

VectorStore = { id, created_at, file_counts, 8 more... }

VectorStoreDeleted = { id, deleted, object }

Beta Vector Stores

File Batches

beta.vector_stores.file_batches

Methods

Cancel Vector Store File Batch ->

VectorStoreFileBatch

post/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

Create Vector Store File Batch ->

VectorStoreFileBatch

post/vector_stores/{vector_store_id}/file_batches

Create a vector store file batch.

List Vector Store Files In A Batch -> CursorPage<

get/vector_stores/{vector_store_id}/file_batches/{batch_id}/files

Returns a list of vector store files in a batch.

Retrieve Vector Store File Batch ->

VectorStoreFileBatch

get/vector_stores/{vector_store_id}/file_batches/{batch_id}

Retrieves a vector store file batch.

Domain types

VectorStoreFileBatch = { id, created_at, file_counts, 3 more... }

Beta Vector Stores

Files

beta.vector_stores.files

Methods

Create Vector Store File ->

post/vector_stores/{vector_store_id}/files

Create a vector store file by attaching a File to a vector store.

Delete Vector Store File ->

VectorStoreFileDeleted

delete/vector_stores/{vector_store_id}/files/{file_id}

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint.

List Vector Store Files -> CursorPage<

get/vector_stores/{vector_store_id}/files

Returns a list of vector store files.

Retrieve Vector Store File ->