AgentOutput interface
Represents an agent that can call the model and use tools.
Properties
| created |
The Unix timestamp, in seconds, representing when this object was created. |
| description | The description of the agent. |
| id | The identifier, which can be referenced in API endpoints. |
| instructions | The system instructions for the agent to use. |
| metadata | A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length. |
| model | The ID of the model to use. |
| name | The name of the agent. |
| object | The object type, which is always assistant. |
| response |
The response format of the tool calls used by this agent. |
| temperature | 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 |
A set of resources that are used by the agent's tools. The resources are specific to the type of tool. For example, the |
| tools | The collection of tools enabled for the agent. |
| topP | 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. |
Property Details
createdAt
The Unix timestamp, in seconds, representing when this object was created.
createdAt: DateProperty Value
Date
description
The description of the agent.
description: null | stringProperty Value
null | string
id
The identifier, which can be referenced in API endpoints.
id: stringProperty Value
string
instructions
The system instructions for the agent to use.
instructions: null | stringProperty Value
null | string
metadata
A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length.
metadata: null | Record<string, string>Property Value
null | Record<string, string>
model
The ID of the model to use.
model: stringProperty Value
string
name
The name of the agent.
name: null | stringProperty Value
null | string
object
The object type, which is always assistant.
object: "assistant"Property Value
"assistant"
responseFormat
The response format of the tool calls used by this agent.
responseFormat?: null | AgentsApiResponseFormatOptionOutputProperty Value
temperature
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.
temperature: null | numberProperty Value
null | number
toolResources
A set of resources that are used by the agent'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.
toolResources: null | ToolResourcesOutputProperty Value
null | ToolResourcesOutput
tools
The collection of tools enabled for the agent.
tools: ToolDefinitionOutput[]Property Value
topP
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.
topP: null | numberProperty Value
null | number
