Docs

Request Headers

authorizationstring*required

Authorization token (required).

Request Path

fownerstring*required

The owner of the GitHub repository containing the function.

frepositorystring*required

The name of the GitHub repository containing the function.

fcommitstringoptional

The commit SHA of the GitHub repository containing the function.

Request Body

FunctionExecutionParamsRemoteFunctionInlineProfileStreamingobject

Parameters for executing a remote function with an inline profile and streaming the response.

Properties
retry_tokenstringoptional

The retry token provided by a previous incomplete or failed function execution.

inputunion*required

The input provided to the function.

Variants
TextRichContentPartobject

A text rich content part.

Properties
type"text"*required
textstring*required

The text content.

ImageRichContentPartobject

An image rich content part.

Properties
type"image_url"*required
image_urlobject*required

The URL of the image and its optional detail level.

Properties
urlstring*required

Either a URL of the image or the base64 encoded image data.

detailenumoptional

Specifies the detail level of the image.

Variants
"auto"
"low"
"high"
AudioRichContentPartobject

An audio rich content part.

Properties
type"input_audio"*required
input_audioobject*required

The audio data and its format.

Properties
datastring*required

Base64 encoded audio data.

formatenum*required

The format of the encoded audio data.

Variants
"wav"
"mp3"
VideoRichContentPartobject

A video rich content part.

Properties
typeenum*required
Variants
"video_url"
"input_video"
video_urlobject*required
Properties
urlstring*required

URL of the video.

FileRichContentPartobject

A file rich content part.

Properties
type"file"*required
fileobject*required

The file to be used as input, either as base64 data, an uploaded file ID, or a URL.

Properties
file_datastringoptional

The base64 encoded file data, used when passing the file to the model as a string.

file_idstringoptional

The ID of an uploaded file to use as input.

filenamestringoptional

The name of the file, used when passing the file to the model as a string.

file_urlstringoptional

The URL of the file, used when passing the file to the model as a URL.

record
Values
Input

The input provided to the function.

array
Items
Input

The input provided to the function.

string
number
boolean
providerobjectoptional

Options for selecting the upstream provider of this completion.

Properties
data_collectionenumoptional

Specifies whether to allow providers which collect data.

Variants
"allow"
"deny"
zdrbooleanoptional

Whether to enforce Zero Data Retention (ZDR) policies when selecting providers.

sortenumoptional

Specifies the sorting strategy for provider selection.

Variants
"price"
"throughput"
"latency"
max_priceobjectoptional
Properties
promptnumberoptional

Maximum price for prompt tokens.

completionnumberoptional

Maximum price for completion tokens.

imagenumberoptional

Maximum price for image generation.

audionumberoptional

Maximum price for audio generation.

requestnumberoptional

Maximum price per request.

preferred_min_throughputnumberoptional

Preferred minimum throughput for the provider.

preferred_max_latencynumberoptional

Preferred maximum latency for the provider.

min_throughputnumberoptional

Minimum throughput for the provider.

max_latencynumberoptional

Maximum latency for the provider.

seedbigintoptional

If specified, upstream systems will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

backoff_max_elapsed_timenumbermin: 0max: 4294967295optional

The maximum total time in milliseconds to spend on retries when a transient error occurs.

first_chunk_timeoutnumbermin: 0max: 4294967295optional

The maximum time in milliseconds to wait for the first chunk of a streaming response.

other_chunk_timeoutnumbermin: 0max: 4294967295optional

The maximum time in milliseconds to wait between subsequent chunks of a streaming response.

profileunion*required

A function profile where remote profiles may omit a commit.

Variants
object
Properties
ownerstring*required

The owner of the GitHub repository containing the profile.

repositorystring*required

The name of the GitHub repository containing the profile.

commitstringoptional

The commit SHA of the GitHub repository containing the profile.

ProfileCommitOptionalArray
streamtrue*required

Whether to stream the response as a series of chunks.

FunctionExecutionParamsRemoteFunctionInlineProfileNonStreamingobject

Parameters for executing a remote function with an inline profile with a unary response.

Properties
retry_tokenstringoptional

The retry token provided by a previous incomplete or failed function execution.

inputunion*required

The input provided to the function.

Variants
TextRichContentPartobject

A text rich content part.

Properties
type"text"*required
textstring*required

The text content.

ImageRichContentPartobject

An image rich content part.

Properties
type"image_url"*required
image_urlobject*required

The URL of the image and its optional detail level.

Properties
urlstring*required

Either a URL of the image or the base64 encoded image data.

detailenumoptional

Specifies the detail level of the image.

Variants
"auto"
"low"
"high"
AudioRichContentPartobject

An audio rich content part.

Properties
type"input_audio"*required
input_audioobject*required

The audio data and its format.

Properties
datastring*required

Base64 encoded audio data.

formatenum*required

The format of the encoded audio data.

Variants
"wav"
"mp3"
VideoRichContentPartobject

A video rich content part.

Properties
typeenum*required
Variants
"video_url"
"input_video"
video_urlobject*required
Properties
urlstring*required

URL of the video.

FileRichContentPartobject

A file rich content part.

Properties
type"file"*required
fileobject*required

The file to be used as input, either as base64 data, an uploaded file ID, or a URL.

Properties
file_datastringoptional

The base64 encoded file data, used when passing the file to the model as a string.

file_idstringoptional

The ID of an uploaded file to use as input.

filenamestringoptional

The name of the file, used when passing the file to the model as a string.

file_urlstringoptional

The URL of the file, used when passing the file to the model as a URL.

record
Values
Input

The input provided to the function.

array
Items
Input

The input provided to the function.

string
number
boolean
providerobjectoptional

Options for selecting the upstream provider of this completion.

Properties
data_collectionenumoptional

Specifies whether to allow providers which collect data.

Variants
"allow"
"deny"
zdrbooleanoptional

Whether to enforce Zero Data Retention (ZDR) policies when selecting providers.

sortenumoptional

Specifies the sorting strategy for provider selection.

Variants
"price"
"throughput"
"latency"
max_priceobjectoptional
Properties
promptnumberoptional

Maximum price for prompt tokens.

completionnumberoptional

Maximum price for completion tokens.

imagenumberoptional

Maximum price for image generation.

audionumberoptional

Maximum price for audio generation.

requestnumberoptional

Maximum price per request.

preferred_min_throughputnumberoptional

Preferred minimum throughput for the provider.

preferred_max_latencynumberoptional

Preferred maximum latency for the provider.

min_throughputnumberoptional

Minimum throughput for the provider.

max_latencynumberoptional

Maximum latency for the provider.

seedbigintoptional

If specified, upstream systems will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

backoff_max_elapsed_timenumbermin: 0max: 4294967295optional

The maximum total time in milliseconds to spend on retries when a transient error occurs.

first_chunk_timeoutnumbermin: 0max: 4294967295optional

The maximum time in milliseconds to wait for the first chunk of a streaming response.

other_chunk_timeoutnumbermin: 0max: 4294967295optional

The maximum time in milliseconds to wait between subsequent chunks of a streaming response.

profileunion*required

A function profile where remote profiles may omit a commit.

Variants
object
Properties
ownerstring*required

The owner of the GitHub repository containing the profile.

repositorystring*required

The name of the GitHub repository containing the profile.

commitstringoptional

The commit SHA of the GitHub repository containing the profile.

ProfileCommitOptionalArray
streamfalseoptional

Whether to stream the response as a series of chunks.

Response Body

idstring*required

The unique identifier of the function execution.

tasksarray*required

The tasks executed as part of the function execution.

Items
object

A function execution task.

Properties
idstring*required

The unique identifier of the function execution.

tasksarray*required

The tasks executed as part of the function execution.

tasks_errorsboolean*required

When true, indicates that one or more tasks encountered errors during execution.

outputunion*required

The output of the function execution.

Variants
number

The scalar output of the function execution.

array

The vector output of the function execution.

Items
number
null
boolean
number
string
array
Items
JsonValue

A JSON value.

record
Values
JsonValue

A JSON value.

errorobjectoptional

When non-null, indicates that an error occurred during the function execution.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

retry_tokenstringoptional

A token which may be used to retry the function execution.

creatednumbermin: 0max: 4294967295*required

The UNIX timestamp (in seconds) when the function execution chunk was created.

functionstringoptional

The unique identifier of the function being executed.

profilestringoptional

The unique identifier of the profile being used.

objectenum*required

The object type.

Variants
"scalar.function.execution"
"vector.function.execution"
usageobject*required

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

indexnumbermin: 0max: 4294967295*required

The index of the task in the sequence of tasks.

task_indexnumbermin: 0max: 4294967295*required

The index of the task amongst all mapped and non-skipped compiled tasks. Used internally.

task_patharray*required

The path of this task which may be used to navigate which nested task this is amongst the root functions tasks and sub-tasks.

Items
numbermin: 0max: 4294967295
object

A vector completion task.

Properties
idstring*required

The unique identifier of the vector completion.

completionsarray*required

The list of chat completions created for this vector completion.

Items
object

A chat completion generated in the pursuit of a vector completion.

Properties
idstring*required

The unique identifier of the chat completion.

upstream_idstring*required

The unique identifier of the upstream chat completion.

choicesarray*required

The list of choices in this chat completion.

Items
object

A choice in a unary chat completion response.

Properties
messageobject*required

A message generated by the assistant.

Properties
contentstringoptional

The content of the message.

refusalstringoptional

The refusal message, if any.

roleenum*required

The role of the message author.

Variants
"assistant"
tool_callsarrayoptional

The tool calls made by the assistant, if any.

Items
object

A function tool call made by the assistant.

Properties
type"function"*required
idstring*required

The unique identifier of the function tool.

functionobject*required
Properties
namestring*required

The name of the function.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning provided by the assistant, if any.

imagesarrayoptional

The images generated by the assistant, if any.

Items
object
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required

The Base64 URL of the generated image.

finish_reasonenum*required

The reason why the assistant ceased to generate further tokens.

Variants
"stop"
"length"
"tool_calls"
"content_filter"
"error"
indexnumbermin: 0max: 4294967295*required

The index of the choice in the list of choices.

logprobsobjectoptional

The log probabilities of the tokens generated by the model.

Properties
contentarrayoptional

The log probabilities of the tokens in the content.

Items
object

The token which was selected by the sampler for this position as well as the logprobabilities of the top options.

Properties
tokenstring*required

The token string which was selected by the sampler.

bytesarrayoptional

The byte representation of the token which was selected by the sampler.

Items
numbermin: 0max: 4294967295
logprobnumber*required

The log probability of the token which was selected by the sampler.

top_logprobsarray*required

The log probabilities of the top tokens for this position.

Items
object

The log probability of a token in the list of top tokens.

Properties
tokenstring*required

The token string.

bytesarrayoptional

The byte representation of the token.

Items
numbermin: 0max: 4294967295
logprobnumberoptional

The log probability of the token.

refusalarrayoptional

The log probabilities of the tokens in the refusal.

Items
object

The token which was selected by the sampler for this position as well as the logprobabilities of the top options.

Properties
tokenstring*required

The token string which was selected by the sampler.

bytesarrayoptional

The byte representation of the token which was selected by the sampler.

Items
numbermin: 0max: 4294967295
logprobnumber*required

The log probability of the token which was selected by the sampler.

top_logprobsarray*required

The log probabilities of the top tokens for this position.

Items
object

The log probability of a token in the list of top tokens.

Properties
tokenstring*required

The token string.

bytesarrayoptional

The byte representation of the token.

Items
numbermin: 0max: 4294967295
logprobnumberoptional

The log probability of the token.

creatednumbermin: 0max: 4294967295*required

The Unix timestamp (in seconds) when the chat completion was created.

modelstring*required

The unique identifier of the Ensemble LLM used for this chat completion.

upstream_modelstring*required

The upstream model used for this chat completion.

object"chat.completion"*required
service_tierstringoptional
system_fingerprintstringoptional
usageobject*required

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

cost_multipliernumber*required

The cost multiplier applied to upstream costs for computing ObjectiveAI costs.

is_byokboolean*required

Whether the completion used a BYOK (Bring Your Own Key) API Key.

providerstringoptional

The provider used for this chat completion.

indexnumbermin: 0max: 4294967295*required

The index of the completion amongst all chat completions.

errorobjectoptional

An error encountered during the generation of this chat completion.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

votesarray*required

The list of votes for responses in the request from the Ensemble LLMs within the provided Ensemble.

Items
object

A vote from an Ensemble LLM within a Vector Completion.

Properties
modelstring*required

The unique identifier of the Ensemble LLM which generated this vote.

ensemble_indexnumbermin: 0max: 4294967295*required

The index of the Ensemble LLM in the Ensemble.

flat_ensemble_indexnumbermin: 0max: 4294967295*required

The flat index of the Ensemble LLM in the expanded Ensemble, accounting for counts.

votearray*required

The vote generated by this Ensemble LLM. It is of the same length of the number of responses provided in the request. If the Ensemble LLM used logprobs, may be a probability distribution; otherwise, one of the responses will have a value of 1 and the rest 0.

Items
number
weightnumber*required

The weight assigned to this vote.

retrybooleanoptional

Whether this vote came from a previous Vector Completion which was retried.

scoresarray*required

The scores for each response in the request, aggregated from the votes of the Ensemble LLMs.

Items
number
weightsarray*required

The weights assigned to each response in the request, aggregated from the votes of the Ensemble LLMs.

Items
number
creatednumbermin: 0max: 4294967295*required

The Unix timestamp (in seconds) when the vector completion was created.

ensemblestring*required

The unique identifier of the Ensemble used for this vector completion.

object"vector.completion"*required
usageobject*required

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

indexnumbermin: 0max: 4294967295*required

The index of the task in the sequence of tasks.

task_indexnumbermin: 0max: 4294967295*required

The index of the task amongst all mapped and non-skipped compiled tasks. Used internally.

task_patharray*required

The path of this task which may be used to navigate which nested task this is amongst the root functions tasks and sub-tasks.

Items
numbermin: 0max: 4294967295
errorobjectoptional

When non-null, indicates that an error occurred during the vector completion task.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

tasks_errorsboolean*required

When true, indicates that one or more tasks encountered errors during execution.

outputunion*required

The output of the function execution.

Variants
number

The scalar output of the function execution.

array

The vector output of the function execution.

Items
number
null
boolean
number
string
array
Items
JsonValue

A JSON value.

record
Values
JsonValue

A JSON value.

errorobjectoptional

When non-null, indicates that an error occurred during the function execution.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

retry_tokenstringoptional

A token which may be used to retry the function execution.

creatednumbermin: 0max: 4294967295*required

The UNIX timestamp (in seconds) when the function execution chunk was created.

functionstringoptional

The unique identifier of the function being executed.

profilestringoptional

The unique identifier of the profile being used.

objectenum*required

The object type.

Variants
"scalar.function.execution"
"vector.function.execution"
usageobject*required

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

Response Body (Streaming)

idstring*required

The unique identifier of the function execution.

tasksarray*required

The tasks executed as part of the function execution.

Items
object

A chunk of a function execution task.

Properties
idstring*required

The unique identifier of the function execution.

tasksarray*required

The tasks executed as part of the function execution.

tasks_errorsbooleanoptional

When true, indicates that one or more tasks encountered errors during execution.

outputunionoptional

The output of the function execution.

Variants
number

The scalar output of the function execution.

array

The vector output of the function execution.

Items
number
null
boolean
number
string
array
Items
JsonValue

A JSON value.

record
Values
JsonValue

A JSON value.

errorobjectoptional

When present, indicates that an error occurred during the function execution.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

retry_tokenstringoptional

A token which may be used to retry the function execution.

creatednumbermin: 0max: 4294967295*required

The UNIX timestamp (in seconds) when the function execution chunk was created.

functionstringoptional

The unique identifier of the function being executed.

profilestringoptional

The unique identifier of the profile being used.

objectenum*required

The object type.

Variants
"scalar.function.execution.chunk"
"vector.function.execution.chunk"
usageobjectoptional

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

indexnumbermin: 0max: 4294967295*required

The index of the task in the sequence of tasks.

task_indexnumbermin: 0max: 4294967295*required

The index of the task amongst all mapped and non-skipped compiled tasks. Used internally.

task_patharray*required

The path of this task which may be used to navigate which nested task this is amongst the root functions tasks and sub-tasks.

Items
numbermin: 0max: 4294967295
object

A chunk of a vector completion task.

Properties
idstring*required

The unique identifier of the vector completion.

completionsarray*required

The list of chat completion chunks created for this vector completion.

Items
object

A chat completion chunk generated in the pursuit of a vector completion.

Properties
idstring*required

The unique identifier of the chat completion.

upstream_idstring*required

The unique identifier of the upstream chat completion.

choicesarray*required

The list of choices in this chunk.

Items
object

A choice in a streaming chat completion response.

Properties
deltaobject*required

A delta in a streaming chat completion response.

Properties
contentstringoptional

The content added in this delta.

refusalstringoptional

The refusal message added in this delta.

roleenumoptional

The role of the message author.

Variants
"assistant"
tool_callsarrayoptional

Tool calls made in this delta.

Items
object

A function tool call made by the assistant.

Properties
indexnumbermin: 0max: 4294967295*required

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

type"function"optional
idstringoptional

The unique identifier of the function tool.

functionobjectoptional
Properties
namestringoptional

The name of the function.

argumentsstringoptional

The arguments passed to the function.

reasoningstringoptional

The reasoning added in this delta.

imagesarrayoptional

Images added in this delta.

Items
object
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required

The Base64 URL of the generated image.

finish_reasonenumoptional

The reason why the assistant ceased to generate further tokens.

Variants
"stop"
"length"
"tool_calls"
"content_filter"
"error"
indexnumbermin: 0max: 4294967295*required

The index of the choice in the list of choices.

logprobsobjectoptional

The log probabilities of the tokens generated by the model.

Properties
contentarrayoptional

The log probabilities of the tokens in the content.

Items
object

The token which was selected by the sampler for this position as well as the logprobabilities of the top options.

Properties
tokenstring*required

The token string which was selected by the sampler.

bytesarrayoptional

The byte representation of the token which was selected by the sampler.

Items
numbermin: 0max: 4294967295
logprobnumber*required

The log probability of the token which was selected by the sampler.

top_logprobsarray*required

The log probabilities of the top tokens for this position.

Items
object

The log probability of a token in the list of top tokens.

Properties
tokenstring*required

The token string.

bytesarrayoptional

The byte representation of the token.

Items
numbermin: 0max: 4294967295
logprobnumberoptional

The log probability of the token.

refusalarrayoptional

The log probabilities of the tokens in the refusal.

Items
object

The token which was selected by the sampler for this position as well as the logprobabilities of the top options.

Properties
tokenstring*required

The token string which was selected by the sampler.

bytesarrayoptional

The byte representation of the token which was selected by the sampler.

Items
numbermin: 0max: 4294967295
logprobnumber*required

The log probability of the token which was selected by the sampler.

top_logprobsarray*required

The log probabilities of the top tokens for this position.

Items
object

The log probability of a token in the list of top tokens.

Properties
tokenstring*required

The token string.

bytesarrayoptional

The byte representation of the token.

Items
numbermin: 0max: 4294967295
logprobnumberoptional

The log probability of the token.

creatednumbermin: 0max: 4294967295*required

The Unix timestamp (in seconds) when the chat completion was created.

modelstring*required

The unique identifier of the Ensemble LLM used for this chat completion.

upstream_modelstring*required

The upstream model used for this chat completion.

object"chat.completion.chunk"*required
service_tierstringoptional
system_fingerprintstringoptional
usageobjectoptional

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

cost_multipliernumber*required

The cost multiplier applied to upstream costs for computing ObjectiveAI costs.

is_byokboolean*required

Whether the completion used a BYOK (Bring Your Own Key) API Key.

providerstringoptional

The provider used for this chat completion.

indexnumbermin: 0max: 4294967295*required

The index of the completion amongst all chat completions.

errorobjectoptional

An error encountered during the generation of this chat completion.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

votesarray*required

The list of votes for responses in the request from the Ensemble LLMs within the provided Ensemble.

Items
object

A vote from an Ensemble LLM within a Vector Completion.

Properties
modelstring*required

The unique identifier of the Ensemble LLM which generated this vote.

ensemble_indexnumbermin: 0max: 4294967295*required

The index of the Ensemble LLM in the Ensemble.

flat_ensemble_indexnumbermin: 0max: 4294967295*required

The flat index of the Ensemble LLM in the expanded Ensemble, accounting for counts.

votearray*required

The vote generated by this Ensemble LLM. It is of the same length of the number of responses provided in the request. If the Ensemble LLM used logprobs, may be a probability distribution; otherwise, one of the responses will have a value of 1 and the rest 0.

Items
number
weightnumber*required

The weight assigned to this vote.

retrybooleanoptional

Whether this vote came from a previous Vector Completion which was retried.

scoresarray*required

The scores for each response in the request, aggregated from the votes of the Ensemble LLMs.

Items
number
weightsarray*required

The weights assigned to each response in the request, aggregated from the votes of the Ensemble LLMs.

Items
number
creatednumbermin: 0max: 4294967295*required

The Unix timestamp (in seconds) when the vector completion was created.

ensemblestring*required

The unique identifier of the Ensemble used for this vector completion.

object"vector.completion.chunk"*required
usageobjectoptional

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

indexnumbermin: 0max: 4294967295*required

The index of the task in the sequence of tasks.

task_indexnumbermin: 0max: 4294967295*required

The index of the task amongst all mapped and non-skipped compiled tasks. Used internally.

task_patharray*required

The path of this task which may be used to navigate which nested task this is amongst the root functions tasks and sub-tasks.

Items
numbermin: 0max: 4294967295
errorobjectoptional

When present, indicates that an error occurred during the vector completion task.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

tasks_errorsbooleanoptional

When true, indicates that one or more tasks encountered errors during execution.

outputunionoptional

The output of the function execution.

Variants
number

The scalar output of the function execution.

array

The vector output of the function execution.

Items
number
null
boolean
number
string
array
Items
JsonValue

A JSON value.

record
Values
JsonValue

A JSON value.

errorobjectoptional

When present, indicates that an error occurred during the function execution.

Properties
codenumbermin: 0max: 4294967295*required

The status code of the error.

messageany*required

The message or details of the error.

retry_tokenstringoptional

A token which may be used to retry the function execution.

creatednumbermin: 0max: 4294967295*required

The UNIX timestamp (in seconds) when the function execution chunk was created.

functionstringoptional

The unique identifier of the function being executed.

profilestringoptional

The unique identifier of the profile being used.

objectenum*required

The object type.

Variants
"scalar.function.execution.chunk"
"vector.function.execution.chunk"
usageobjectoptional

Token and cost usage statistics for the completion.

Properties
completion_tokensnumbermin: 0max: 4294967295*required

The number of tokens generated in the completion.

prompt_tokensnumbermin: 0max: 4294967295*required

The number of tokens in the prompt.

total_tokensnumbermin: 0max: 4294967295*required

The total number of tokens used in the prompt or generated in the completion.

completion_tokens_detailsobjectoptional

Detailed breakdown of generated completion tokens.

Properties
accepted_prediction_tokensnumbermin: 0max: 4294967295optional

The number of accepted prediction tokens in the completion.

audio_tokensnumbermin: 0max: 4294967295optional

The number of generated audio tokens in the completion.

reasoning_tokensnumbermin: 0max: 4294967295optional

The number of generated reasoning tokens in the completion.

rejected_prediction_tokensnumbermin: 0max: 4294967295optional

The number of rejected prediction tokens in the completion.

prompt_tokens_detailsobjectoptional

Detailed breakdown of prompt tokens.

Properties
audio_tokensnumbermin: 0max: 4294967295optional

The number of audio tokens in the prompt.

cached_tokensnumbermin: 0max: 4294967295optional

The number of cached tokens in the prompt.

cache_write_tokensnumbermin: 0max: 4294967295optional

The number of prompt tokens written to cache.

video_tokensnumbermin: 0max: 4294967295optional

The number of video tokens in the prompt.

costnumber*required

The cost in credits incurred for this completion.

cost_detailsobjectoptional

Detailed breakdown of upstream costs incurred.

Properties
upstream_inference_costnumberoptional

The cost incurred upstream.

upstream_upstream_inference_costnumberoptional

The cost incurred by upstream's upstream.

total_costnumber*required

The total cost in credits incurred including upstream costs.

Objective Artificial Intelligence, Inc.