API Reference

Beta

Threads

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create thread and run

Deprecated: The Assistants API is deprecated in favor of the Responses API

$ openai beta:threads create-and-run

POST/threads/runs

Create a thread and run it in one request.

ParametersExpand Collapse

--assistant-id: string

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

--instructions: optional string

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

--max-completion-tokens: optional 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: optional 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: optional map[string]

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.

--model: optional string or 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: optional boolean

Whether to enable parallel function calling during tool use.

--response-format: optional "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

--temperature: optional 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: optional object { messages, metadata, tool_resources }

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

--tool-choice: optional "none" or "auto" or "required" or AssistantToolChoice { type, function }

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: optional object { 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.

--tool: optional array of AssistantTool

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

--top-p: optional 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: optional object { type, last_messages }

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

ReturnsExpand Collapse

run: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

assistant_stream_event: object { data, event, enabled } or object { data, event } or object { data, event } or 21 more

Represents an event emitted when streaming a Run.

Each event in a server-sent events stream has an event and data property:

event: thread.created
data: {"id": "thread_123", "object": "thread", ...}

We emit events whenever a new object is created, transitions to a new state, or is being streamed in parts (deltas). For example, we emit thread.run.created when a new run is created, thread.run.completed when a run completes, and so on. When an Assistant chooses to create a message during a run, we emit a thread.message.created event, a thread.message.in_progress event, many thread.message.delta events, and finally a thread.message.completed event.

We may add additional events over time, so we recommend handling unknown events gracefully in your code. See the Assistants API quickstart to learn how to integrate the Assistants API with streaming.

thread.created: object { data, event, enabled }

Occurs when a new thread is created.

data: object { id, created_at, metadata, 2 more }

Represents a thread that contains messages.

id: string

The identifier, which can be referenced in API endpoints.

created_at: number

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

metadata: map[string]

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.

object: "thread"

The object type, which is always thread.

tool_resources: object { 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.

code_interpreter: optional object { file_ids }

file_ids: optional array of string

A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

file_search: optional object { vector_store_ids }

vector_store_ids: optional array of string

The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

event: "thread.created"

enabled: optional boolean

Whether to enable input audio transcription.

thread.run.created: object { data, event }

Occurs when a new run is created.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.created"

thread.run.queued: object { data, event }

Occurs when a run moves to a queued status.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.queued"

thread.run.in_progress: object { data, event }

Occurs when a run moves to an in_progress status.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.in_progress"

thread.run.requires_action: object { data, event }

Occurs when a run moves to a requires_action status.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.requires_action"

thread.run.completed: object { data, event }

Occurs when a run is completed.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.completed"

thread.run.incomplete: object { data, event }

Occurs when a run ends with status incomplete.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.incomplete"

thread.run.failed: object { data, event }

Occurs when a run fails.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.failed"

thread.run.cancelling: object { data, event }

Occurs when a run moves to a cancelling status.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.cancelling"

thread.run.cancelled: object { data, event }

Occurs when a run is cancelled.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.cancelled"

thread.run.expired: object { data, event }

Occurs when a run expires.

data: object { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

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

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expires_at: number

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

failed_at: number

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

incomplete_details: object { reason }

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

reason: optional "max_completion_tokens" or "max_prompt_tokens"

The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

"max_completion_tokens"

"max_prompt_tokens"

instructions: string

The instructions that the assistant used for this run.

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded" or "invalid_prompt"

One of server_error, rate_limit_exceeded, or invalid_prompt.

"server_error"

"rate_limit_exceeded"

"invalid_prompt"

message: string

A human-readable description of the error.

max_completion_tokens: number

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

max_prompt_tokens: number

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

metadata: map[string]

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.

model: string

The model that the assistant used for this run.

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action: object { submit_tool_outputs, type }

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

submit_tool_outputs: object { tool_calls }

Details on the tool outputs needed for this run to continue.

tool_calls: array of RequiredActionFunctionToolCall { id, function, type }

A list of the relevant tool calls.

id: string

The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

function: object { arguments, name }

The function definition.

arguments: string

The arguments that the model expects you to pass to the function.

name: string

The name of the function.

type: "function"

The type of tool call the output is required for. For now, this is always function.

type: "submit_tool_outputs"

For now, this is always submit_tool_outputs.

response_format: "auto" or ResponseFormatText { type } or ResponseFormatJSONObject { type } or ResponseFormatJSONSchema { json_schema, type }

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.

union_member_0: "auto"

auto is the default value

response_format_text: object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

response_format_json_object: object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

response_format_json_schema: object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

json_schema: object { name, description, schema, strict }

Structured Outputs configuration options, including a JSON Schema.

name: string

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the response format is for, used by the model to determine how to respond in the format.

schema: optional map[unknown]

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict: optional boolean

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

type: "json_schema"

The type of response format being defined. Always json_schema.

started_at: number

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

status: "queued" or "in_progress" or "requires_action" or 6 more

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

"queued"

"in_progress"

"requires_action"

"cancelling"

"cancelled"

"failed"

"completed"

"incomplete"

"expired"

thread_id: string

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

tool_choice: "none" or "auto" or "required" or AssistantToolChoice { type, function }

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.

Auto: "none" or "auto" or "required"

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.

"none"

"auto"

"required"

assistant_tool_choice: object { type, function }

Specifies a tool the model should use. Use to force the model to call a specific tool.

type: "function" or "code_interpreter" or "file_search"

The type of the tool. If type is function, the function name must be set

"function"

"code_interpreter"

"file_search"

function: optional object { name }

name: string

The name of the function to call.

tools: array of AssistantTool

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

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

file_search_tool: object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

function_tool: object { function, type }

function: object { name, description, parameters, strict }

name: string

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description: optional string

A description of what the function does, used by the model to choose when and how to call the function.

parameters: optional map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

strict: optional boolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

type: "function"

The type of tool being defined: function

truncation_strategy: object { type, last_messages }

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

type: "auto" or "last_messages"

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.

"auto"

"last_messages"

last_messages: optional number

The number of most recent messages from the thread when constructing the context for the run.

usage: object { completion_tokens, prompt_tokens, total_tokens }

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.).

completion_tokens: number

Number of completion tokens used over the course of the run.

prompt_tokens: number

Number of prompt tokens used over the course of the run.

total_tokens: number

Total number of tokens used (prompt + completion).

temperature: optional number

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

top_p: optional number

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

event: "thread.run.expired"

thread.run.step.created: object { data, event }

Occurs when a run step is created.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.created"

thread.run.step.in_progress: object { data, event }

Occurs when a run step moves to an in_progress state.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.in_progress"

thread.run.step.delta: object { data, event }

Occurs when parts of a run step are being streamed.

data: object { id, delta, object }

Represents a run step delta i.e. any changed fields on a run step during streaming.

id: string

The identifier of the run step, which can be referenced in API endpoints.

delta: object { step_details }

The delta containing the fields that have changed on the run step.

step_details: optional RunStepDeltaMessageDelta { type, message_creation } or ToolCallDeltaObject { type, tool_calls }

The details of the run step.

run_step_delta_message_delta: object { type, message_creation }

Details of the message creation by the run step.

type: "message_creation"

Always message_creation.

message_creation: optional object { message_id }

message_id: optional string

The ID of the message that was created by this run step.

tool_call_delta_object: object { type, tool_calls }

Details of the tool call.

type: "tool_calls"

Always tool_calls.

tool_calls: optional array of ToolCallDelta

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call_delta: object { index, type, id, code_interpreter }

Details of the Code Interpreter tool call the run step was involved in.

index: number

The index of the tool call in the tool calls array.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

id: optional string

The ID of the tool call.

code_interpreter: optional object { input, outputs }

The Code Interpreter tool call definition.

input: optional string

The input to the Code Interpreter tool call.

outputs: optional array of CodeInterpreterLogs { index, type, logs } or CodeInterpreterOutputImage { index, type, image }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

code_interpreter_logs: object { index, type, logs }

Text output from the Code Interpreter tool call as part of a run step.

index: number

The index of the output in the outputs array.

type: "logs"

Always logs.

logs: optional string

The text output from the Code Interpreter tool call.

code_interpreter_output_image: object { index, type, image }

index: number

The index of the output in the outputs array.

type: "image"

Always image.

image: optional object { file_id }

file_id: optional string

The file ID of the image.

file_search_tool_call_delta: object { file_search, index, type, id }

file_search: unknown

For now, this is always going to be an empty object.

index: number

The index of the tool call in the tool calls array.

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

id: optional string

The ID of the tool call object.

function_tool_call_delta: object { index, type, id, function }

index: number

The index of the tool call in the tool calls array.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

id: optional string

The ID of the tool call object.

function: optional object { arguments, name, output }

The definition of the function that was called.

arguments: optional string

The arguments passed to the function.

name: optional string

The name of the function.

output: optional string

The output of the function. This will be null if the outputs have not been submitted yet.

object: "thread.run.step.delta"

The object type, which is always thread.run.step.delta.

event: "thread.run.step.delta"

thread.run.step.completed: object { data, event }

Occurs when a run step is completed.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.completed"

thread.run.step.failed: object { data, event }

Occurs when a run step fails.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.failed"

thread.run.step.cancelled: object { data, event }

Occurs when a run step is cancelled.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.cancelled"

thread.run.step.expired: object { data, event }

Occurs when a run step expires.

data: object { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

id: string

The identifier of the run step, which can be referenced in API endpoints.

assistant_id: string

The ID of the assistant associated with the run step.

cancelled_at: number

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

completed_at: number

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

created_at: number

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

expired_at: number

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

failed_at: number

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

last_error: object { code, message }

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

code: "server_error" or "rate_limit_exceeded"

One of server_error or rate_limit_exceeded.

"server_error"

"rate_limit_exceeded"

message: string

A human-readable description of the error.

metadata: map[string]

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.

object: "thread.run.step"

The object type, which is always thread.run.step.

run_id: string

The ID of the run that this run step is a part of.

status: "in_progress" or "cancelled" or "failed" or 2 more

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

"in_progress"

"cancelled"

"failed"

"completed"

"expired"

step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type }

The details of the run step.

message_creation_step_details: object { message_creation, type }

Details of the message creation by the run step.

message_creation: object { message_id }

message_id: string

The ID of the message that was created by this run step.

type: "message_creation"

Always message_creation.

tool_calls_step_details: object { tool_calls, type }

Details of the tool call.

tool_calls: array of ToolCall

An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

code_interpreter_tool_call: object { id, code_interpreter, type }

Details of the Code Interpreter tool call the run step was involved in.

id: string

The ID of the tool call.

code_interpreter: object { input, outputs }

The Code Interpreter tool call definition.

input: string

The input to the Code Interpreter tool call.

outputs: array of object { logs, type } or object { image, type }

The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

logs: object { logs, type }

Text output from the Code Interpreter tool call as part of a run step.

logs: string

The text output from the Code Interpreter tool call.

type: "logs"

Always logs.

image: object { image, type }

image: object { file_id }

file_id: string

The file ID of the image.

type: "image"

Always image.

type: "code_interpreter"

The type of tool call. This is always going to be code_interpreter for this type of tool call.

file_search_tool_call: object { id, file_search, type }

id: string

The ID of the tool call object.

file_search: object { ranking_options, results }

For now, this is always going to be an empty object.

ranking_options: optional object { ranker, score_threshold }

The ranking options for the file search.

ranker: "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

"auto"

"default_2024_08_21"

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

results: optional array of object { file_id, file_name, score, content }

The results of the file search.

file_id: string

The ID of the file that result was found in.

file_name: string

The name of the file that result was found in.

score: number

The score of the result. All values must be a floating point number between 0 and 1.

content: optional array of object { text, type }

The content of the result that was found. The content is only included if requested via the include query parameter.

text: optional string

The text content of the file.

type: optional "text"

The type of the content.

"text"

type: "file_search"

The type of tool call. This is always going to be file_search for this type of tool call.

function_tool_call: object { id, function, type }

id: string

The ID of the tool call object.

function: object { arguments, name, output }

The definition of the function that was called.

arguments: string

The arguments passed to the function.

name: string

The name of the function.

output: string

The output of the function. This will be null if the outputs have not been submitted yet.

type: "function"

The type of tool call. This is always going to be function for this type of tool call.

type: "tool_calls"

Always tool_calls.

thread_id: string

The ID of the thread that was run.

type: "message_creation" or "tool_calls"

The type of run step, which can be either message_creation or tool_calls.

"message_creation"

"tool_calls"

usage: object { completion_tokens, prompt_tokens, total_tokens }

Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.

completion_tokens: number

Number of completion tokens used over the course of the run step.

prompt_tokens: number

Number of prompt tokens used over the course of the run step.

total_tokens: number

Total number of tokens used (prompt + completion).

event: "thread.run.step.expired"

thread.message.created: object { data, event }

Occurs when a message is created.

data: object { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

If applicable, the ID of the assistant that authored this message.

attachments: array of object { file_id, tools }

A list of files attached to the message, and the tools they were added to.

file_id: optional string

The ID of the file to attach to the message.

tools: optional array of CodeInterpreterTool { type } or object { type }

The tools to add this file to.

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

AssistantToolsFileSearchTypeOnly: object { type }

completed_at: number

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

content: array of MessageContent

The content of the message in array of text and/or images.

image_file_content_block: object { image_file, type }

References an image File in the content of a message.

image_file: object { file_id, detail }

file_id: string

The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

type: "image_file"

Always image_file.

image_url_content_block: object { image_url, type }

References an image URL in the content of a message.

image_url: object { url, detail }

url: string

The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

"auto"

"low"

"high"

type: "image_url"

The type of the content part.

text_content_block: object { text, type }

The text content that is part of a message.

text: object { annotations, value }

annotations: array of Annotation

file_citation_annotation: object { end_index, file_citation, start_index, 2 more }

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the “file_search” tool to search files.

end_index: number

file_citation: object { file_id }

file_id: string

The ID of the specific File the citation is from.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_citation"

Always file_citation.

file_path_annotation: object { end_index, file_path, start_index, 2 more }

A URL for the file that’s generated when the assistant used the code_interpreter tool to generate a file.

end_index: number

file_path: object { file_id }

file_id: string

The ID of the file that was generated.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_path"

Always file_path.

value: string

The data that makes up the text.

type: "text"

Always text.

refusal_content_block: object { refusal, type }

The refusal content generated by the assistant.

refusal: string

type: "refusal"

Always refusal.

created_at: number

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

incomplete_at: number

The Unix timestamp (in seconds) for when the message was marked as incomplete.

incomplete_details: object { reason }

On an incomplete message, details about why the message is incomplete.

reason: "content_filter" or "max_tokens" or "run_cancelled" or 2 more

The reason the message is incomplete.

"content_filter"

"max_tokens"

"run_cancelled"

"run_expired"

"run_failed"

metadata: map[string]

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.

object: "thread.message"

The object type, which is always thread.message.

role: "user" or "assistant"

The entity that produced the message. One of user or assistant.

"user"

"assistant"

run_id: string

The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.

status: "in_progress" or "incomplete" or "completed"

The status of the message, which can be either in_progress, incomplete, or completed.

"in_progress"

"incomplete"

"completed"

thread_id: string

The thread ID that this message belongs to.

event: "thread.message.created"

thread.message.in_progress: object { data, event }

Occurs when a message moves to an in_progress state.

data: object { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

If applicable, the ID of the assistant that authored this message.

attachments: array of object { file_id, tools }

A list of files attached to the message, and the tools they were added to.

file_id: optional string

The ID of the file to attach to the message.

tools: optional array of CodeInterpreterTool { type } or object { type }

The tools to add this file to.

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

AssistantToolsFileSearchTypeOnly: object { type }

completed_at: number

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

content: array of MessageContent

The content of the message in array of text and/or images.

image_file_content_block: object { image_file, type }

References an image File in the content of a message.

image_file: object { file_id, detail }

file_id: string

The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

type: "image_file"

Always image_file.

image_url_content_block: object { image_url, type }

References an image URL in the content of a message.

image_url: object { url, detail }

url: string

The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

"auto"

"low"

"high"

type: "image_url"

The type of the content part.

text_content_block: object { text, type }

The text content that is part of a message.

text: object { annotations, value }

annotations: array of Annotation

file_citation_annotation: object { end_index, file_citation, start_index, 2 more }

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the “file_search” tool to search files.

end_index: number

file_citation: object { file_id }

file_id: string

The ID of the specific File the citation is from.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_citation"

Always file_citation.

file_path_annotation: object { end_index, file_path, start_index, 2 more }

A URL for the file that’s generated when the assistant used the code_interpreter tool to generate a file.

end_index: number

file_path: object { file_id }

file_id: string

The ID of the file that was generated.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_path"

Always file_path.

value: string

The data that makes up the text.

type: "text"

Always text.

refusal_content_block: object { refusal, type }

The refusal content generated by the assistant.

refusal: string

type: "refusal"

Always refusal.

created_at: number

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

incomplete_at: number

The Unix timestamp (in seconds) for when the message was marked as incomplete.

incomplete_details: object { reason }

On an incomplete message, details about why the message is incomplete.

reason: "content_filter" or "max_tokens" or "run_cancelled" or 2 more

The reason the message is incomplete.

"content_filter"

"max_tokens"

"run_cancelled"

"run_expired"

"run_failed"

metadata: map[string]

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.

object: "thread.message"

The object type, which is always thread.message.

role: "user" or "assistant"

The entity that produced the message. One of user or assistant.

"user"

"assistant"

run_id: string

The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.

status: "in_progress" or "incomplete" or "completed"

The status of the message, which can be either in_progress, incomplete, or completed.

"in_progress"

"incomplete"

"completed"

thread_id: string

The thread ID that this message belongs to.

event: "thread.message.in_progress"

thread.message.delta: object { data, event }

Occurs when parts of a Message are being streamed.

data: object { id, delta, object }

Represents a message delta i.e. any changed fields on a message during streaming.

id: string

The identifier of the message, which can be referenced in API endpoints.

delta: object { content, role }

The delta containing the fields that have changed on the Message.

content: optional array of MessageContentDelta

The content of the message in array of text and/or images.

image_file_delta_block: object { index, type, image_file }

References an image File in the content of a message.

index: number

The index of the content part in the message.

type: "image_file"

Always image_file.

image_file: optional object { detail, file_id }

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

file_id: optional string

The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

text_delta_block: object { index, type, text }

The text content that is part of a message.

index: number

The index of the content part in the message.

type: "text"

Always text.

text: optional object { annotations, value }

annotations: optional array of AnnotationDelta

file_citation_delta_annotation: object { index, type, end_index, 3 more }

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the “file_search” tool to search files.

index: number

The index of the annotation in the text content part.

type: "file_citation"

Always file_citation.

end_index: optional number

file_citation: optional object { file_id, quote }

file_id: optional string

The ID of the specific File the citation is from.

quote: optional string

The specific quote in the file.

start_index: optional number

text: optional string

The text in the message content that needs to be replaced.

file_path_delta_annotation: object { index, type, end_index, 3 more }

A URL for the file that’s generated when the assistant used the code_interpreter tool to generate a file.

index: number

The index of the annotation in the text content part.

type: "file_path"

Always file_path.

end_index: optional number

file_path: optional object { file_id }

file_id: optional string

The ID of the file that was generated.

start_index: optional number

text: optional string

The text in the message content that needs to be replaced.

value: optional string

The data that makes up the text.

refusal_delta_block: object { index, type, refusal }

The refusal content that is part of a message.

index: number

The index of the refusal part in the message.

type: "refusal"

Always refusal.

refusal: optional string

image_url_delta_block: object { index, type, image_url }

References an image URL in the content of a message.

index: number

The index of the content part in the message.

type: "image_url"

Always image_url.

image_url: optional object { detail, url }

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

url: optional string

The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

role: optional "user" or "assistant"

The entity that produced the message. One of user or assistant.

"user"

"assistant"

object: "thread.message.delta"

The object type, which is always thread.message.delta.

event: "thread.message.delta"

thread.message.completed: object { data, event }

Occurs when a message is completed.

data: object { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

If applicable, the ID of the assistant that authored this message.

attachments: array of object { file_id, tools }

A list of files attached to the message, and the tools they were added to.

file_id: optional string

The ID of the file to attach to the message.

tools: optional array of CodeInterpreterTool { type } or object { type }

The tools to add this file to.

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

AssistantToolsFileSearchTypeOnly: object { type }

completed_at: number

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

content: array of MessageContent

The content of the message in array of text and/or images.

image_file_content_block: object { image_file, type }

References an image File in the content of a message.

image_file: object { file_id, detail }

file_id: string

The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

type: "image_file"

Always image_file.

image_url_content_block: object { image_url, type }

References an image URL in the content of a message.

image_url: object { url, detail }

url: string

The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

"auto"

"low"

"high"

type: "image_url"

The type of the content part.

text_content_block: object { text, type }

The text content that is part of a message.

text: object { annotations, value }

annotations: array of Annotation

file_citation_annotation: object { end_index, file_citation, start_index, 2 more }

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the “file_search” tool to search files.

end_index: number

file_citation: object { file_id }

file_id: string

The ID of the specific File the citation is from.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_citation"

Always file_citation.

file_path_annotation: object { end_index, file_path, start_index, 2 more }

A URL for the file that’s generated when the assistant used the code_interpreter tool to generate a file.

end_index: number

file_path: object { file_id }

file_id: string

The ID of the file that was generated.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_path"

Always file_path.

value: string

The data that makes up the text.

type: "text"

Always text.

refusal_content_block: object { refusal, type }

The refusal content generated by the assistant.

refusal: string

type: "refusal"

Always refusal.

created_at: number

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

incomplete_at: number

The Unix timestamp (in seconds) for when the message was marked as incomplete.

incomplete_details: object { reason }

On an incomplete message, details about why the message is incomplete.

reason: "content_filter" or "max_tokens" or "run_cancelled" or 2 more

The reason the message is incomplete.

"content_filter"

"max_tokens"

"run_cancelled"

"run_expired"

"run_failed"

metadata: map[string]

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.

object: "thread.message"

The object type, which is always thread.message.

role: "user" or "assistant"

The entity that produced the message. One of user or assistant.

"user"

"assistant"

run_id: string

The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.

status: "in_progress" or "incomplete" or "completed"

The status of the message, which can be either in_progress, incomplete, or completed.

"in_progress"

"incomplete"

"completed"

thread_id: string

The thread ID that this message belongs to.

event: "thread.message.completed"

thread.message.incomplete: object { data, event }

Occurs when a message ends before it is completed.

data: object { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

id: string

The identifier, which can be referenced in API endpoints.

assistant_id: string

If applicable, the ID of the assistant that authored this message.

attachments: array of object { file_id, tools }

A list of files attached to the message, and the tools they were added to.

file_id: optional string

The ID of the file to attach to the message.

tools: optional array of CodeInterpreterTool { type } or object { type }

The tools to add this file to.

code_interpreter_tool: object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

AssistantToolsFileSearchTypeOnly: object { type }

completed_at: number

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

content: array of MessageContent

The content of the message in array of text and/or images.

image_file_content_block: object { image_file, type }

References an image File in the content of a message.

image_file: object { file_id, detail }

file_id: string

The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

"auto"

"low"

"high"

type: "image_file"

Always image_file.

image_url_content_block: object { image_url, type }

References an image URL in the content of a message.

image_url: object { url, detail }

url: string

The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

detail: optional "auto" or "low" or "high"

Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

"auto"

"low"

"high"

type: "image_url"

The type of the content part.

text_content_block: object { text, type }

The text content that is part of a message.

text: object { annotations, value }

annotations: array of Annotation

file_citation_annotation: object { end_index, file_citation, start_index, 2 more }

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the “file_search” tool to search files.

end_index: number

file_citation: object { file_id }

file_id: string

The ID of the specific File the citation is from.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_citation"

Always file_citation.

file_path_annotation: object { end_index, file_path, start_index, 2 more }

A URL for the file that’s generated when the assistant used the code_interpreter tool to generate a file.

end_index: number

file_path: object { file_id }

file_id: string

The ID of the file that was generated.

start_index: number

text: string

The text in the message content that needs to be replaced.

type: "file_path"

Always file_path.

value: string

The data that makes up the text.

type: "text"

Always text.

refusal_content_block: object { refusal, type }

The refusal content generated by the assistant.

refusal: string

type: "refusal"

Always refusal.

created_at: number

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

incomplete_at: number

The Unix timestamp (in seconds) for when the message was marked as incomplete.

incomplete_details: object { reason }

On an incomplete message, details about why the message is incomplete.

reason: "content_filter" or "max_tokens" or "run_cancelled" or 2 more

The reason the message is incomplete.

"content_filter"

"max_tokens"

"run_cancelled"

"run_expired"

"run_failed"

metadata: map[string]

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.

object: "thread.message"

The object type, which is always thread.message.

role: "user" or "assistant"

The entity that produced the message. One of user or assistant.

"user"

"assistant"

run_id: string

The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.

status: "in_progress" or "incomplete" or "completed"

The status of the message, which can be either in_progress, incomplete, or completed.

"in_progress"

"incomplete"

"completed"

thread_id: string

The thread ID that this message belongs to.

event: "thread.message.incomplete"

error_event: object { data, event }

Occurs when an error occurs. This can happen due to an internal server error or a timeout.

data: object { code, message, param, type }

code: string

message: string

param: string

type: string

event: "error"

Create thread and run

CLI Tool

HTTP

TypeScript

Python

Java

Go

Ruby

CLI Tool

openai beta:threads create-and-run \
  --api-key 'My API Key' \
  --assistant-id assistant_id

{
  "id": "run_abc123",
  "object": "thread.run",
  "created_at": 1699076792,
  "assistant_id": "asst_abc123",
  "thread_id": "thread_abc123",
  "status": "queued",
  "started_at": null,
  "expires_at": 1699077392,
  "cancelled_at": null,
  "failed_at": null,
  "completed_at": null,
  "required_action": null,
  "last_error": null,
  "model": "gpt-4o",
  "instructions": "You are a helpful assistant.",
  "tools": [],
  "tool_resources": {},
  "metadata": {},
  "temperature": 1.0,
  "top_p": 1.0,
  "max_completion_tokens": null,
  "max_prompt_tokens": null,
  "truncation_strategy": {
    "type": "auto",
    "last_messages": null
  },
  "incomplete_details": null,
  "usage": null,
  "response_format": "auto",
  "tool_choice": "auto",
  "parallel_tool_calls": true
}

Returns Examples

{
  "id": "run_abc123",
  "object": "thread.run",
  "created_at": 1699076792,
  "assistant_id": "asst_abc123",
  "thread_id": "thread_abc123",
  "status": "queued",
  "started_at": null,
  "expires_at": 1699077392,
  "cancelled_at": null,
  "failed_at": null,
  "completed_at": null,
  "required_action": null,
  "last_error": null,
  "model": "gpt-4o",
  "instructions": "You are a helpful assistant.",
  "tools": [],
  "tool_resources": {},
  "metadata": {},
  "temperature": 1.0,
  "top_p": 1.0,
  "max_completion_tokens": null,
  "max_prompt_tokens": null,
  "truncation_strategy": {
    "type": "auto",
    "last_messages": null
  },
  "incomplete_details": null,
  "usage": null,
  "response_format": "auto",
  "tool_choice": "auto",
  "parallel_tool_calls": true
}