Beta
BetaChatKit
ModelsExpand Collapse
ChatKitWorkflow = object { id, state_variables, tracing, version } Workflow metadata and state returned for the session.
Workflow metadata and state returned for the session.
Identifier of the workflow backing the session.
state_variables: map[string or boolean or number]State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided.
State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided.
tracing: object { enabled } Tracing settings applied to the workflow.
Tracing settings applied to the workflow.
Indicates whether tracing is enabled.
Specific workflow version used for the session. Defaults to null when using the latest deployment.
BetaChatKitSessions
Cancel chat session
Create ChatKit session
BetaChatKitThreads
List ChatKit thread items
Retrieve ChatKit thread
Delete ChatKit thread
List ChatKit threads
ModelsExpand Collapse
ChatSession = object { id, chatkit_configuration, client_secret, 7 more } Represents a ChatKit session and its resolved configuration.
Represents a ChatKit session and its resolved configuration.
Identifier for the ChatKit session.
Resolved ChatKit feature configuration for the session.
Ephemeral client secret that authenticates session requests.
Unix timestamp (in seconds) for when the session expires.
Convenience copy of the per-minute request limit.
Type discriminator that is always chatkit.session.
Resolved rate limit values.
Current lifecycle state of the session.
User identifier associated with the session.
Workflow metadata for the session.
ChatSessionAutomaticThreadTitling = object { enabled } Automatic thread title preferences for the session.
Automatic thread title preferences for the session.
Whether automatic thread titling is enabled.
ChatSessionChatKitConfiguration = object { automatic_thread_titling, file_upload, history } ChatKit configuration for the session.
ChatKit configuration for the session.
Automatic thread titling preferences.
Upload settings for the session.
History retention configuration.
ChatSessionChatKitConfigurationParam = object { automatic_thread_titling, file_upload, history } Optional per-session configuration settings for ChatKit behavior.
Optional per-session configuration settings for ChatKit behavior.
automatic_thread_titling: optional object { enabled } Configuration for automatic thread titling. When omitted, automatic thread titling is enabled by default.
Configuration for automatic thread titling. When omitted, automatic thread titling is enabled by default.
Enable automatic thread title generation. Defaults to true.
file_upload: optional object { enabled, max_file_size, max_files } Configuration for upload enablement and limits. When omitted, uploads are disabled by default (max_files 10, max_file_size 512 MB).
Configuration for upload enablement and limits. When omitted, uploads are disabled by default (max_files 10, max_file_size 512 MB).
Enable uploads for this session. Defaults to false.
Maximum size in megabytes for each uploaded file. Defaults to 512 MB, which is the maximum allowable size.
Maximum number of files that can be uploaded to the session. Defaults to 10.
history: optional object { enabled, recent_threads } Configuration for chat history retention. When omitted, history is enabled by default with no limit on recent_threads (null).
Configuration for chat history retention. When omitted, history is enabled by default with no limit on recent_threads (null).
Enables chat users to access previous ChatKit threads. Defaults to true.
Number of recent ChatKit threads users have access to. Defaults to unlimited when unset.
ChatSessionExpiresAfterParam = object { anchor, seconds } Controls when the session expires relative to an anchor timestamp.
Controls when the session expires relative to an anchor timestamp.
Base timestamp used to calculate expiration. Currently fixed to created_at.
Number of seconds after the anchor when the session expires.
ChatSessionFileUpload = object { enabled, max_file_size, max_files } Upload permissions and limits applied to the session.
Upload permissions and limits applied to the session.
Indicates if uploads are enabled for the session.
Maximum upload size in megabytes.
Maximum number of uploads allowed during the session.
ChatSessionHistory = object { enabled, recent_threads } History retention preferences returned for the session.
History retention preferences returned for the session.
Indicates if chat history is persisted for the session.
Number of prior threads surfaced in history views. Defaults to null when all history is retained.
ChatSessionRateLimits = object { max_requests_per_1_minute } Active per-minute request limit for the session.
Active per-minute request limit for the session.
Maximum allowed requests per one-minute window.
ChatSessionRateLimitsParam = object { max_requests_per_1_minute } Controls request rate limits for the session.
Controls request rate limits for the session.
Maximum number of requests allowed per minute for the session. Defaults to 10.
ChatSessionStatus = "active" or "expired" or "cancelled"
ChatSessionWorkflowParam = object { id, state_variables, tracing, version } Workflow reference and overrides applied to the chat session.
Workflow reference and overrides applied to the chat session.
Identifier for the workflow invoked by the session.
state_variables: optional map[string or boolean or number]State variables forwarded to the workflow. Keys may be up to 64 characters, values must be primitive types, and the map defaults to an empty object.
State variables forwarded to the workflow. Keys may be up to 64 characters, values must be primitive types, and the map defaults to an empty object.
tracing: optional object { enabled } Optional tracing overrides for the workflow invocation. When omitted, tracing is enabled by default.
Optional tracing overrides for the workflow invocation. When omitted, tracing is enabled by default.
Whether tracing is enabled during the session. Defaults to true.
Specific workflow version to run. Defaults to the latest deployed version.
ChatKitAttachment = object { id, mime_type, name, 2 more } Attachment metadata included on thread items.
Attachment metadata included on thread items.
Identifier for the attachment.
MIME type of the attachment.
Original display name for the attachment.
Preview URL for rendering the attachment inline.
type: "image" or "file"Attachment discriminator.
Attachment discriminator.
ChatKitResponseOutputText = object { annotations, text, type } Assistant response text accompanied by optional annotations.
Assistant response text accompanied by optional annotations.
annotations: array of object { source, type } or object { source, type } Ordered list of annotations attached to the response text.
Ordered list of annotations attached to the response text.
File = object { source, type } Annotation that references an uploaded file.
Annotation that references an uploaded file.
source: object { filename, type } File attachment referenced by the annotation.
File attachment referenced by the annotation.
Filename referenced by the annotation.
Type discriminator that is always file.
Type discriminator that is always file for this annotation.
URL = object { source, type } Annotation that references a URL.
Annotation that references a URL.
source: object { type, url } URL referenced by the annotation.
URL referenced by the annotation.
Type discriminator that is always url.
URL referenced by the annotation.
Type discriminator that is always url for this annotation.
Assistant generated text.
Type discriminator that is always output_text.
ChatKitThread = object { id, created_at, object, 3 more } Represents a ChatKit thread and its current status.
Represents a ChatKit thread and its current status.
Identifier of the thread.
Unix timestamp (in seconds) for when the thread was created.
Type discriminator that is always chatkit.thread.
status: object { type } or object { reason, type } or object { reason, type } Current status for the thread. Defaults to active for newly created threads.
Current status for the thread. Defaults to active for newly created threads.
Active = object { type } Indicates that a thread is active.
Indicates that a thread is active.
Status discriminator that is always active.
Locked = object { reason, type } Indicates that a thread is locked and cannot accept new input.
Indicates that a thread is locked and cannot accept new input.
Reason that the thread was locked. Defaults to null when no reason is recorded.
Status discriminator that is always locked.
Closed = object { reason, type } Indicates that a thread has been closed.
Indicates that a thread has been closed.
Reason that the thread was closed. Defaults to null when no reason is recorded.
Status discriminator that is always closed.
Optional human-readable title for the thread. Defaults to null when no title has been generated.
Free-form string that identifies your end user who owns the thread.
ChatKitThreadAssistantMessageItem = object { id, content, created_at, 3 more } Assistant-authored message within a thread.
Assistant-authored message within a thread.
Identifier of the thread item.
Ordered assistant response segments.
Ordered assistant response segments.
annotations: array of object { source, type } or object { source, type } Ordered list of annotations attached to the response text.
Ordered list of annotations attached to the response text.
File = object { source, type } Annotation that references an uploaded file.
Annotation that references an uploaded file.
source: object { filename, type } File attachment referenced by the annotation.
File attachment referenced by the annotation.
Filename referenced by the annotation.
Type discriminator that is always file.
Type discriminator that is always file for this annotation.
URL = object { source, type } Annotation that references a URL.
Annotation that references a URL.
source: object { type, url } URL referenced by the annotation.
URL referenced by the annotation.
Type discriminator that is always url.
URL referenced by the annotation.
Type discriminator that is always url for this annotation.
Assistant generated text.
Type discriminator that is always output_text.
Unix timestamp (in seconds) for when the item was created.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
Type discriminator that is always chatkit.assistant_message.
ChatKitThreadItemList = object { data, first_id, has_more, 2 more } A paginated list of thread items rendered for the ChatKit API.
A paginated list of thread items rendered for the ChatKit API.
data: array of ChatKitThreadUserMessageItem { id, attachments, content, 5 more } or ChatKitThreadAssistantMessageItem { id, content, created_at, 3 more } or ChatKitWidgetItem { id, created_at, object, 3 more } or 3 moreA list of items
A list of items
ChatKitThreadUserMessageItem = object { id, attachments, content, 5 more } User-authored messages within a thread.
User-authored messages within a thread.
Identifier of the thread item.
Attachments associated with the user message. Defaults to an empty list.
Attachments associated with the user message. Defaults to an empty list.
Identifier for the attachment.
MIME type of the attachment.
Original display name for the attachment.
Preview URL for rendering the attachment inline.
type: "image" or "file"Attachment discriminator.
Attachment discriminator.
content: array of object { text, type } or object { text, type } Ordered content elements supplied by the user.
Ordered content elements supplied by the user.
InputText = object { text, type } Text block that a user contributed to the thread.
Text block that a user contributed to the thread.
Plain-text content supplied by the user.
Type discriminator that is always input_text.
QuotedText = object { text, type } Quoted snippet that the user referenced in their message.
Quoted snippet that the user referenced in their message.
Quoted text content.
Type discriminator that is always quoted_text.
Unix timestamp (in seconds) for when the item was created.
inference_options: object { model, tool_choice } Inference overrides applied to the message. Defaults to null when unset.
Inference overrides applied to the message. Defaults to null when unset.
Model name that generated the response. Defaults to null when using the session default.
tool_choice: object { id } Preferred tool to invoke. Defaults to null when ChatKit should auto-select.
Preferred tool to invoke. Defaults to null when ChatKit should auto-select.
Identifier of the requested tool.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
ChatKitThreadAssistantMessageItem = object { id, content, created_at, 3 more } Assistant-authored message within a thread.
Assistant-authored message within a thread.
Identifier of the thread item.
Ordered assistant response segments.
Ordered assistant response segments.
annotations: array of object { source, type } or object { source, type } Ordered list of annotations attached to the response text.
Ordered list of annotations attached to the response text.
File = object { source, type } Annotation that references an uploaded file.
Annotation that references an uploaded file.
source: object { filename, type } File attachment referenced by the annotation.
File attachment referenced by the annotation.
Filename referenced by the annotation.
Type discriminator that is always file.
Type discriminator that is always file for this annotation.
URL = object { source, type } Annotation that references a URL.
Annotation that references a URL.
source: object { type, url } URL referenced by the annotation.
URL referenced by the annotation.
Type discriminator that is always url.
URL referenced by the annotation.
Type discriminator that is always url for this annotation.
Assistant generated text.
Type discriminator that is always output_text.
Unix timestamp (in seconds) for when the item was created.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
Type discriminator that is always chatkit.assistant_message.
ChatKitWidgetItem = object { id, created_at, object, 3 more } Thread item that renders a widget payload.
Thread item that renders a widget payload.
Identifier of the thread item.
Unix timestamp (in seconds) for when the item was created.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
Type discriminator that is always chatkit.widget.
Serialized widget payload rendered in the UI.
ChatKitClientToolCall = object { id, arguments, call_id, 7 more } Record of a client side tool invocation initiated by the assistant.
Record of a client side tool invocation initiated by the assistant.
Identifier of the thread item.
JSON-encoded arguments that were sent to the tool.
Identifier for the client tool call.
Unix timestamp (in seconds) for when the item was created.
Tool name that was invoked.
Type discriminator that is always chatkit.thread_item.
JSON-encoded output captured from the tool. Defaults to null while execution is in progress.
status: "in_progress" or "completed"Execution status for the tool call.
Execution status for the tool call.
Identifier of the parent thread.
Type discriminator that is always chatkit.client_tool_call.
ChatKitTask = object { id, created_at, heading, 5 more } Task emitted by the workflow to show progress and status updates.
Task emitted by the workflow to show progress and status updates.
Identifier of the thread item.
Unix timestamp (in seconds) for when the item was created.
Optional heading for the task. Defaults to null when not provided.
Type discriminator that is always chatkit.thread_item.
Optional summary that describes the task. Defaults to null when omitted.
task_type: "custom" or "thought"Subtype for the task.
Subtype for the task.
Identifier of the parent thread.
Type discriminator that is always chatkit.task.
ChatKitTaskGroup = object { id, created_at, object, 3 more } Collection of workflow tasks grouped together in the thread.
Collection of workflow tasks grouped together in the thread.
Identifier of the thread item.
Unix timestamp (in seconds) for when the item was created.
Type discriminator that is always chatkit.thread_item.
tasks: array of object { heading, summary, type } Tasks included in the group.
Tasks included in the group.
Optional heading for the grouped task. Defaults to null when not provided.
Optional summary that describes the grouped task. Defaults to null when omitted.
type: "custom" or "thought"Subtype for the grouped task.
Subtype for the grouped task.
Identifier of the parent thread.
Type discriminator that is always chatkit.task_group.
The ID of the first item in the list.
Whether there are more items available.
The ID of the last item in the list.
The type of object returned, must be list.
ChatKitThreadUserMessageItem = object { id, attachments, content, 5 more } User-authored messages within a thread.
User-authored messages within a thread.
Identifier of the thread item.
Attachments associated with the user message. Defaults to an empty list.
Attachments associated with the user message. Defaults to an empty list.
Identifier for the attachment.
MIME type of the attachment.
Original display name for the attachment.
Preview URL for rendering the attachment inline.
type: "image" or "file"Attachment discriminator.
Attachment discriminator.
content: array of object { text, type } or object { text, type } Ordered content elements supplied by the user.
Ordered content elements supplied by the user.
InputText = object { text, type } Text block that a user contributed to the thread.
Text block that a user contributed to the thread.
Plain-text content supplied by the user.
Type discriminator that is always input_text.
QuotedText = object { text, type } Quoted snippet that the user referenced in their message.
Quoted snippet that the user referenced in their message.
Quoted text content.
Type discriminator that is always quoted_text.
Unix timestamp (in seconds) for when the item was created.
inference_options: object { model, tool_choice } Inference overrides applied to the message. Defaults to null when unset.
Inference overrides applied to the message. Defaults to null when unset.
Model name that generated the response. Defaults to null when using the session default.
tool_choice: object { id } Preferred tool to invoke. Defaults to null when ChatKit should auto-select.
Preferred tool to invoke. Defaults to null when ChatKit should auto-select.
Identifier of the requested tool.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
ChatKitWidgetItem = object { id, created_at, object, 3 more } Thread item that renders a widget payload.
Thread item that renders a widget payload.
Identifier of the thread item.
Unix timestamp (in seconds) for when the item was created.
Type discriminator that is always chatkit.thread_item.
Identifier of the parent thread.
Type discriminator that is always chatkit.widget.
Serialized widget payload rendered in the UI.
BetaAssistants
ModelsExpand Collapse
Assistant = object { id, created_at, description, 10 more } Represents an assistant that can call the model and use tools.
Represents an assistant that can call the model and use tools.
The identifier, which can be referenced in API endpoints.
The Unix timestamp (in seconds) for when the assistant was created.
The description of the assistant. The maximum length is 512 characters.
The system instructions that the assistant uses. The maximum length is 256,000 characters.
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.
ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
The name of the assistant. The maximum length is 256 characters.
The object type, which is always assistant.
tools: array of CodeInterpreterTool { type } or FileSearchTool { type, file_search } or FunctionTool { function, type } A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.
A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.
CodeInterpreterTool = object { type }
The type of tool being defined: code_interpreter
FileSearchTool = object { 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.
Overrides for the file search tool.
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.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
FunctionTool = object { function, type }
The type of tool being defined: function
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.
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.
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.
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.
code_interpreter: optional object { file_ids }
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 }
The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.
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.
AssistantDeleted = object { id, deleted, object }
AssistantStreamEvent = object { data, event, enabled } or object { data, event } or object { data, event } or 22 moreRepresents 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.
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.
UnionMember13 = object { data, event } Occurs when parts of a run step are being streamed.
Occurs when parts of a run step are being streamed.
Represents a run step delta i.e. any changed fields on a run step during streaming.
UnionMember20 = object { data, event } Occurs when parts of a Message are being streamed.
Occurs when parts of a Message are being streamed.
Represents a message delta i.e. any changed fields on a message during streaming.
ErrorEvent = object { data, event } Occurs when an error occurs. This can happen due to an internal server error or a timeout.
Occurs when an error occurs. This can happen due to an internal server error or a timeout.
DoneEvent = object { data, event } Occurs when a stream ends.
Occurs when a stream ends.
CodeInterpreterTool = object { type }
The type of tool being defined: code_interpreter
FileSearchTool = object { 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.
Overrides for the file search tool.
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.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
FunctionTool = object { function, type }
The type of tool being defined: function
MessageStreamEvent = object { data, event } or object { data, event } or object { data, event } or 2 moreOccurs when a message is created.
Occurs when a message is created.
UnionMember2 = object { data, event } Occurs when parts of a Message are being streamed.
Occurs when parts of a Message are being streamed.
Represents a message delta i.e. any changed fields on a message during streaming.
RunStepStreamEvent = object { data, event } or object { data, event } or object { data, event } or 4 moreOccurs when a run step is created.
Occurs when a run step is created.
UnionMember2 = object { data, event } Occurs when parts of a run step are being streamed.
Occurs when parts of a run step are being streamed.
Represents a run step delta i.e. any changed fields on a run step during streaming.
RunStreamEvent = object { data, event } or object { data, event } or object { data, event } or 7 moreOccurs when a new run is created.
Occurs when a new run is created.
BetaThreads
ModelsExpand Collapse
AssistantResponseFormatOption = "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.
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.
auto is the default value
ResponseFormatText = object { type } Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
ResponseFormatJSONObject = 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.
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.
The type of response format being defined. Always json_object.
ResponseFormatJSONSchema = object { json_schema, type } JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
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.
Structured Outputs configuration options, including a JSON Schema.
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.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
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.
The type of response format being defined. Always json_schema.
AssistantToolChoice = object { type, function } Specifies a tool the model should use. Use to force the model to call a specific tool.
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
The type of the tool. If type is function, the function name must be set
AssistantToolChoiceFunction = object { name }
The name of the function to call.
AssistantToolChoiceOption = "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.
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.
UnionMember0 = "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 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.
AssistantToolChoice = object { type, function } Specifies a tool the model should use. Use to force the model to call a specific tool.
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
The type of the tool. If type is function, the function name must be set
Thread = object { id, created_at, metadata, 2 more } Represents a thread that contains messages.
Represents a thread that contains messages.
The identifier, which can be referenced in API endpoints.
The Unix timestamp (in seconds) for when the thread was created.
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.
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.
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 }
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 }
The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.
ThreadDeleted = object { id, deleted, object }
BetaThreadsRuns
ModelsExpand Collapse
RequiredActionFunctionToolCall = object { id, function, type } Tool call objects
Tool call objects
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.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
Run = object { id, assistant_id, cancelled_at, 24 more } Represents an execution run on a thread.
Represents an execution run on a thread.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
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.
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.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
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.
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.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
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.
The model that the assistant used for this run.
The object type, which is always thread.run.
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.
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.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
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.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
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.
The Unix timestamp (in seconds) for when the run was started.
status: "queued" or "in_progress" or "requires_action" or 6 moreThe status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
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.
tools: array of CodeInterpreterTool { type } or FileSearchTool { type, file_search } or FunctionTool { function, type } The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
CodeInterpreterTool = object { type }
The type of tool being defined: code_interpreter
FileSearchTool = object { 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.
Overrides for the file search tool.
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.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
FunctionTool = object { function, type }
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.
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.
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.
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.).
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.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
BetaThreadsRunsSteps
ModelsExpand Collapse
CodeInterpreterLogs = object { index, type, logs } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The index of the output in the outputs array.
Always logs.
The text output from the Code Interpreter tool call.
CodeInterpreterOutputImage = object { index, type, image }
The index of the output in the outputs array.
Always image.
image: optional object { file_id }
The file ID of the image.
CodeInterpreterToolCall = object { id, code_interpreter, type } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogOutput = object { logs, type } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
CodeInterpreterImageOutput = object { image, type }
image: object { file_id }
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
CodeInterpreterToolCallDelta = object { index, type, id, code_interpreter } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
The ID of the tool call.
code_interpreter: optional object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogs = object { index, type, logs } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The index of the output in the outputs array.
Always logs.
The text output from the Code Interpreter tool call.
CodeInterpreterOutputImage = object { index, type, image }
The index of the output in the outputs array.
Always image.
image: optional object { file_id }
The file ID of the image.
FileSearchToolCall = object { id, file_search, type }
The ID of the tool call object.
file_search: object { ranking_options, results } For now, this is always going to be an empty object.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
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.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
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.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
FileSearchToolCallDelta = object { file_search, index, type, id }
For now, this is always going to be an empty object.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be file_search for this type of tool call.
The ID of the tool call object.
FunctionToolCall = object { id, function, type }
The ID of the tool call object.
function: object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
FunctionToolCallDelta = object { index, type, id, function }
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be function for this type of tool call.
The ID of the tool call object.
function: optional object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
MessageCreationStepDetails = object { message_creation, type } Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: object { message_id }
The ID of the message that was created by this run step.
Always message_creation.
RunStep = object { id, assistant_id, cancelled_at, 13 more } Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
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.
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.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
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.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: "in_progress" or "cancelled" or "failed" or 2 moreThe status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: MessageCreationStepDetails { message_creation, type } or ToolCallsStepDetails { tool_calls, type } The details of the run step.
The details of the run step.
MessageCreationStepDetails = object { message_creation, type } Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: object { message_id }
The ID of the message that was created by this run step.
Always message_creation.
ToolCallsStepDetails = object { tool_calls, type } Details of the tool call.
Details of the tool call.
tool_calls: array of CodeInterpreterToolCall { id, code_interpreter, type } or FileSearchToolCall { id, file_search, type } or FunctionToolCall { id, function, type } 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.
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.
CodeInterpreterToolCall = object { id, code_interpreter, type } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogOutput = object { logs, type } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
CodeInterpreterImageOutput = object { image, type }
image: object { file_id }
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
FileSearchToolCall = object { id, file_search, type }
The ID of the tool call object.
file_search: object { ranking_options, results } For now, this is always going to be an empty object.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
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.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
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.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
FunctionToolCall = object { id, function, type }
The ID of the tool call object.
function: object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
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.
The type of run step, which can be either message_creation or 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.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
RunStepDeltaEvent = object { id, delta, object } Represents a run step delta i.e. any changed fields on a run step during streaming.
Represents a run step delta i.e. any changed fields on a run step during streaming.
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.
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.
The details of the run step.
RunStepDeltaMessageDelta = object { type, message_creation } Details of the message creation by the run step.
Details of the message creation by the run step.
Always message_creation.
message_creation: optional object { message_id }
The ID of the message that was created by this run step.
ToolCallDeltaObject = object { type, tool_calls } Details of the tool call.
Details of the tool call.
Always tool_calls.
tool_calls: optional array of CodeInterpreterToolCallDelta { index, type, id, code_interpreter } or FileSearchToolCallDelta { file_search, index, type, id } or FunctionToolCallDelta { index, type, id, function } 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.
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.
CodeInterpreterToolCallDelta = object { index, type, id, code_interpreter } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
The ID of the tool call.
code_interpreter: optional object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogs = object { index, type, logs } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The index of the output in the outputs array.
Always logs.
The text output from the Code Interpreter tool call.
CodeInterpreterOutputImage = object { index, type, image }
The index of the output in the outputs array.
Always image.
image: optional object { file_id }
The file ID of the image.
FileSearchToolCallDelta = object { file_search, index, type, id }
For now, this is always going to be an empty object.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be file_search for this type of tool call.
The ID of the tool call object.
FunctionToolCallDelta = object { index, type, id, function }
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be function for this type of tool call.
The ID of the tool call object.
function: optional object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The object type, which is always thread.run.step.delta.
RunStepDeltaMessageDelta = object { type, message_creation } Details of the message creation by the run step.
Details of the message creation by the run step.
Always message_creation.
message_creation: optional object { message_id }
The ID of the message that was created by this run step.
ToolCallDeltaObject = object { type, tool_calls } Details of the tool call.
Details of the tool call.
Always tool_calls.
tool_calls: optional array of CodeInterpreterToolCallDelta { index, type, id, code_interpreter } or FileSearchToolCallDelta { file_search, index, type, id } or FunctionToolCallDelta { index, type, id, function } 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.
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.
CodeInterpreterToolCallDelta = object { index, type, id, code_interpreter } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
The ID of the tool call.
code_interpreter: optional object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogs = object { index, type, logs } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The index of the output in the outputs array.
Always logs.
The text output from the Code Interpreter tool call.
CodeInterpreterOutputImage = object { index, type, image }
The index of the output in the outputs array.
Always image.
image: optional object { file_id }
The file ID of the image.
FileSearchToolCallDelta = object { file_search, index, type, id }
For now, this is always going to be an empty object.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be file_search for this type of tool call.
The ID of the tool call object.
FunctionToolCallDelta = object { index, type, id, function }
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be function for this type of tool call.
The ID of the tool call object.
function: optional object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
ToolCallsStepDetails = object { tool_calls, type } Details of the tool call.
Details of the tool call.
tool_calls: array of CodeInterpreterToolCall { id, code_interpreter, type } or FileSearchToolCall { id, file_search, type } or FunctionToolCall { id, function, type } 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.
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.
CodeInterpreterToolCall = object { id, code_interpreter, type } Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: object { input, outputs } The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
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.
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.
CodeInterpreterLogOutput = object { logs, type } Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
CodeInterpreterImageOutput = object { image, type }
image: object { file_id }
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
FileSearchToolCall = object { id, file_search, type }
The ID of the tool call object.
file_search: object { ranking_options, results } For now, this is always going to be an empty object.
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.
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.
The ranker to use for the file search. If not specified will use the auto ranker.
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.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
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.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
FunctionToolCall = object { id, function, type }
The ID of the tool call object.
function: object { arguments, name, output } The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
BetaThreadsMessages
ModelsExpand Collapse
FileCitationAnnotation = 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.
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.
file_citation: object { file_id }
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
FileCitationDeltaAnnotation = 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.
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.
The index of the annotation in the text content part.
Always file_citation.
file_citation: optional object { file_id, quote }
The ID of the specific File the citation is from.
The specific quote in the file.
The text in the message content that needs to be replaced.
FilePathAnnotation = 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.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: object { file_id }
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
FilePathDeltaAnnotation = 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.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
The index of the annotation in the text content part.
Always file_path.
file_path: optional object { file_id }
The ID of the file that was generated.
The text in the message content that needs to be replaced.
ImageFile = object { file_id, detail }
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.
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.
ImageFileDelta = 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.
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.
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.
ImageFileDeltaBlock = object { index, type, image_file } References an image File in the content of a message.
References an image File in the content of a message.
The index of the content part in the message.
Always image_file.
ImageURL = object { url, detail }
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
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
ImageURLContentBlock = object { image_url, type } References an image URL in the content of a message.
References an image URL in the content of a message.
The type of the content part.
ImageURLDelta = 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.
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high.
The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
ImageURLDeltaBlock = object { index, type, image_url } References an image URL in the content of a message.
References an image URL in the content of a message.
The index of the content part in the message.
Always image_url.
Message = object { id, assistant_id, attachments, 11 more } Represents a message within a thread.
Represents a message within a thread.
The identifier, which can be referenced in API endpoints.
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.
A list of files attached to the message, and the tools they were added to.
The ID of the file to attach to the message.
The tools to add this file to.
The tools to add this file to.
CodeInterpreterTool = object { type }
The type of tool being defined: code_interpreter
FileSearchTool = object { type }
The type of tool being defined: file_search
The Unix timestamp (in seconds) for when the message was completed.
content: array of ImageFileContentBlock { image_file, type } or ImageURLContentBlock { image_url, type } or TextContentBlock { text, type } or RefusalContentBlock { refusal, type } The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
ImageURLContentBlock = object { image_url, type } References an image URL in the content of a message.
References an image URL in the content of a message.
The type of the content part.
TextContentBlock = object { text, type } The text content that is part of a message.
The text content that is part of a message.
Always text.
RefusalContentBlock = object { refusal, type } The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
The Unix timestamp (in seconds) for when the message was created.
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.
On an incomplete message, details about why the message is incomplete.
reason: "content_filter" or "max_tokens" or "run_cancelled" or 2 moreThe reason the message is incomplete.
The reason the message is incomplete.
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.
The object type, which is always thread.message.
role: "user" or "assistant"The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
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.
The status of the message, which can be either in_progress, incomplete, or completed.
The thread ID that this message belongs to.
MessageDeleted = object { id, deleted, object }
MessageDelta = object { content, role } The delta containing the fields that have changed on the Message.
The delta containing the fields that have changed on the Message.
content: optional array of ImageFileDeltaBlock { index, type, image_file } or TextDeltaBlock { index, type, text } or RefusalDeltaBlock { index, type, refusal } or ImageURLDeltaBlock { index, type, image_url } The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
ImageFileDeltaBlock = object { index, type, image_file } References an image File in the content of a message.
References an image File in the content of a message.
The index of the content part in the message.
Always image_file.
TextDeltaBlock = object { index, type, text } The text content that is part of a message.
The text content that is part of a message.
The index of the content part in the message.
Always text.
RefusalDeltaBlock = object { index, type, refusal } The refusal content that is part of a message.
The refusal content that is part of a message.
The index of the refusal part in the message.
Always refusal.
ImageURLDeltaBlock = object { index, type, image_url } References an image URL in the content of a message.
References an image URL in the content of a message.
The index of the content part in the message.
Always image_url.
role: optional "user" or "assistant"The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
MessageDeltaEvent = object { id, delta, object } Represents a message delta i.e. any changed fields on a message during streaming.
Represents a message delta i.e. any changed fields on a message during streaming.
The identifier of the message, which can be referenced in API endpoints.
The delta containing the fields that have changed on the Message.
The object type, which is always thread.message.delta.
RefusalContentBlock = object { refusal, type } The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
RefusalDeltaBlock = object { index, type, refusal } The refusal content that is part of a message.
The refusal content that is part of a message.
The index of the refusal part in the message.
Always refusal.
Text = object { annotations, value }
annotations: array of FileCitationAnnotation { end_index, file_citation, start_index, 2 more } or FilePathAnnotation { end_index, file_path, start_index, 2 more }
FileCitationAnnotation = 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.
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.
file_citation: object { file_id }
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
FilePathAnnotation = 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.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: object { file_id }
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
The data that makes up the text.
TextContentBlock = object { text, type } The text content that is part of a message.
The text content that is part of a message.
Always text.
TextContentBlockParam = object { text, type } The text content that is part of a message.
The text content that is part of a message.
Text content to be sent to the model
Always text.
TextDelta = object { annotations, value }
annotations: optional array of FileCitationDeltaAnnotation { index, type, end_index, 3 more } or FilePathDeltaAnnotation { index, type, end_index, 3 more }
FileCitationDeltaAnnotation = 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.
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.
The index of the annotation in the text content part.
Always file_citation.
file_citation: optional object { file_id, quote }
The ID of the specific File the citation is from.
The specific quote in the file.
The text in the message content that needs to be replaced.
FilePathDeltaAnnotation = 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.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
The index of the annotation in the text content part.
Always file_path.
file_path: optional object { file_id }
The ID of the file that was generated.
The text in the message content that needs to be replaced.
The data that makes up the text.
TextDeltaBlock = object { index, type, text } The text content that is part of a message.
The text content that is part of a message.
The index of the content part in the message.
Always text.