CompletionUsage
objectUsage statistics for the completion request.
Number of tokens in the generated completion.
Default:0
Number of tokens in the prompt.
Default:0
Total number of tokens used in the request (prompt + completion).
Default:0
Breakdown of tokens used in a completion.
Show Child Parameters
Breakdown of tokens used in the prompt.
Show Child Parameters
CostsResult
objectThe aggregated costs details of the specific time bucket.
Allowed values:organization.costs.result
The monetary value in its associated currency.
Show Child Parameters
When group_by=line_item, this field provides the line item of the grouped costs result.
When group_by=project_id, this field provides the project ID of the grouped costs result.
CreateAssistantRequest
objectAny OfID 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.
Example:gpt-4o
The name of the assistant. The maximum length is 256 characters.
<= 256 characters
The description of the assistant. The maximum length is 512 characters.
<= 512 characters
The system instructions that the assistant uses. The maximum length is 256,000 characters.
<= 256000 characters
o1 and o3-mini models only
Constrains effort on reasoning for
reasoning models.
Currently supported values are low, medium, and high. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
Allowed values:lowmediumhigh
Default:medium
One OfA 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.
Default:[]
<= 128 items
Show Child Parameters
A set of resources that are used by the assistant’s tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
Show Child Parameters
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.
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Default:1
>= 0<= 2
Example:1
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
Default:1
>= 0<= 1
Example:1
One Ofauto is the default value
Allowed values:auto
CreateChatCompletionFunctionResponse
objectRepresents a chat completion response returned by model, based on the provided input.
A unique identifier for the chat completion.
A list of chat completion choices. Can be more than one if n is greater than 1.
Show Child Parameters
The Unix timestamp (in seconds) of when the chat completion was created.
The model used for the chat completion.
This fingerprint represents the backend configuration that the model runs with.
Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.
The object type, which is always chat.completion.
Allowed values:chat.completion
Usage statistics for the completion request.
Show Child Parameters
CreateChatCompletionImageResponse
objectRepresents a streamed chunk of a chat completion response returned by model, based on the provided input.