Docs

Request Path

idstring*required

The ID of the Ensemble.

Response Body

idstring*required

The unique identifier for the Ensemble.

llmsarray*required

The list of LLMs that make up the ensemble.

Items
object

An LLM to be used within an Ensemble, including its unique identifier, optional fallbacks, and count.

Properties
modelstring*required

The full ID of the LLM to use.

output_modeenum*required

For Vector Completions only, specifies the LLM's voting output mode. For "instruction", the assistant is instructed to output a key. For "json_schema", the assistant is constrained to output a valid key using a JSON schema. For "tool_call", the assistant is instructed to output a tool call to select the key.

Variants
"instruction"
"json_schema"
"tool_call"
synthetic_reasoningbooleanoptional

For Vector Completions only, whether to use synthetic reasoning prior to voting. Works for any LLM, even those that do not have native reasoning capabilities.

top_logprobsnumbermin: 0max: 20optional

For Vector Completions only, whether to use logprobs to make the vote probabilistic. This means that the LLM can vote for multiple keys based on their logprobabilities. Allows LLMs to express native uncertainty when voting.

prefix_messagesarrayoptional

A list of messages exchanged in a chat conversation. These will be prepended to every prompt sent to this LLM. Useful for setting context or influencing behavior.

Items
DeveloperMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"developer"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

SystemMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"system"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

UserMessageobject

Messages sent by an end user, containing prompts or additional context information.

Properties
role"user"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

ToolMessageobject

Messages sent by tools in response to tool calls made by the assistant.

Properties
role"tool"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

tool_call_idstring*required

The ID of the tool call that this message is responding to.

AssistantMessageobject

Messages sent by the model in response to user messages.

Properties
role"assistant"*required
contentunionoptional

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusalstringoptional

The refusal message by the assistant.

tool_callsarrayoptional

Tool calls made by the assistant.

Items
AssistantMessageToolCallFunctionobject

A function tool call made by the assistant.

Properties
type"function"*required
idstring*required

The unique identifier for the tool call.

functionobject*required

The name and arguments of the function called.

Properties
namestring*required

The name of the function called.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning provided by the assistant.

suffix_messagesarrayoptional

A list of messages exchanged in a chat conversation. These will be appended to every prompt sent to this LLM. Useful for setting context or influencing behavior.

Items
DeveloperMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"developer"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

SystemMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"system"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

UserMessageobject

Messages sent by an end user, containing prompts or additional context information.

Properties
role"user"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

ToolMessageobject

Messages sent by tools in response to tool calls made by the assistant.

Properties
role"tool"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

tool_call_idstring*required

The ID of the tool call that this message is responding to.

AssistantMessageobject

Messages sent by the model in response to user messages.

Properties
role"assistant"*required
contentunionoptional

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusalstringoptional

The refusal message by the assistant.

tool_callsarrayoptional

Tool calls made by the assistant.

Items
AssistantMessageToolCallFunctionobject

A function tool call made by the assistant.

Properties
type"function"*required
idstring*required

The unique identifier for the tool call.

functionobject*required

The name and arguments of the function called.

Properties
namestring*required

The name of the function called.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning provided by the assistant.

frequency_penaltynumbermin: -2max: 2optional

This setting aims to control the repetition of tokens based on how often they appear in the input. It tries to use less frequently those tokens that appear more in the input, proportional to how frequently they occur. Token penalty scales with the number of occurrences. Negative values will encourage token reuse.

logit_biasrecordoptional

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

Values
numbermin: -100max: 100
max_completion_tokensnumbermin: 0max: 2147483647optional

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

presence_penaltynumbermin: -2max: 2optional

This setting aims to control the presence of tokens in the output. It tries to encourage the model to use tokens that are less present in the input, proportional to their presence in the input. Token presence scales with the number of occurrences. Negative values will encourage more diverse token usage.

stopunionoptional

The assistant will stop when any of the provided strings are generated.

Variants
StopStringstring

Generation will stop when this string is generated.

StopStringsarray

Generation will stop when any of these strings are generated.

Items
StopStringstring
temperaturenumbermin: 0max: 2optional

This setting influences the variety in the model’s responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.

top_pnumbermin: 0max: 1optional

This setting limits the model’s choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model’s responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

max_tokensnumbermin: 0max: 2147483647optional

This sets the upper limit for the number of tokens the model can generate in response. It won’t produce more than this limit. The maximum value is the context length minus the prompt length.

min_pnumbermin: 0max: 1optional

Represents the minimum probability for a token to be considered, relative to the probability of the most likely token. (The value changes depending on the confidence level of the most probable token.) If your Min-P is set to 0.1, that means it will only allow for tokens that are at least 1/10th as probable as the best possible option.

providerobjectoptional

Options for selecting the upstream provider of this model.

Properties
allow_fallbacksbooleanoptional

Whether to allow fallback providers if the preferred provider is unavailable.

require_parametersbooleanoptional

Whether to require that the provider supports all specified parameters.

orderarrayoptional

An ordered list of provider names to use when selecting a provider for this model.

Items
ProviderNamestring
onlyarrayoptional

A list of provider names to restrict selection to when selecting a provider for this model.

Items
ProviderNamestring
ignorearrayoptional

A list of provider names to ignore when selecting a provider for this model.

Items
ProviderNamestring
quantizationsarrayoptional

Specifies the quantizations to allow when selecting providers for this model.

Items
"int4"
"int8"
"fp4"
"fp6"
"fp8"
"fp16"
"bf16"
"fp32"
"unknown"
reasoningobjectoptional

Options for controlling reasoning behavior of the model.

Properties
enabledbooleanoptional

Enables or disables reasoning for supported models.

max_tokensnumbermin: 0max: 2147483647optional

The maximum number of tokens to use for reasoning in a response.

effortenumoptional

Constrains effort on reasoning for supported reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Variants
"none"
"minimal"
"low"
"medium"
"high"
"xhigh"
summary_verbosityenumoptional

Controls the verbosity of the reasoning summary for supported reasoning models.

Variants
"auto"
"concise"
"detailed"
repetition_penaltynumbermin: 0max: 2optional

Helps to reduce the repetition of tokens from the input. A higher value makes the model less likely to repeat tokens, but too high a value can make the output less coherent (often with run-on sentences that lack small words). Token penalty scales based on original token’s probability.

top_anumbermin: 0max: 1optional

Consider only the top tokens with “sufficiently high” probabilities based on the probability of the most likely token. Think of it like a dynamic Top-P. A lower Top-A value focuses the choices based on the highest probability token but with a narrower scope. A higher Top-A value does not necessarily affect the creativity of the output, but rather refines the filtering process based on the maximum probability.

top_knumbermin: 0max: 2147483647optional

This limits the model’s choice of tokens at each step, making it choose from a smaller set. A value of 1 means the model will always pick the most likely next token, leading to predictable results. By default this setting is disabled, making the model to consider all choices.

verbosityenumoptional

Controls the verbosity and length of the model response. Lower values produce more concise responses, while higher values produce more detailed and comprehensive responses.

Variants
"low"
"medium"
"high"
idstring*required

The unique identifier for the Ensemble LLM.

countnumbermin: 1max: 4294967295optional

A count greater than one effectively means that there are multiple instances of this LLM in an ensemble.

fallbacksarrayoptional

A list of fallback LLMs to use if the primary LLM fails.

Items
object

An LLM to be used within an Ensemble or standalone with Chat Completions, including its unique identifier.

Properties
modelstring*required

The full ID of the LLM to use.

output_modeenum*required

For Vector Completions only, specifies the LLM's voting output mode. For "instruction", the assistant is instructed to output a key. For "json_schema", the assistant is constrained to output a valid key using a JSON schema. For "tool_call", the assistant is instructed to output a tool call to select the key.

Variants
"instruction"
"json_schema"
"tool_call"
synthetic_reasoningbooleanoptional

For Vector Completions only, whether to use synthetic reasoning prior to voting. Works for any LLM, even those that do not have native reasoning capabilities.

top_logprobsnumbermin: 0max: 20optional

For Vector Completions only, whether to use logprobs to make the vote probabilistic. This means that the LLM can vote for multiple keys based on their logprobabilities. Allows LLMs to express native uncertainty when voting.

prefix_messagesarrayoptional

A list of messages exchanged in a chat conversation. These will be prepended to every prompt sent to this LLM. Useful for setting context or influencing behavior.

Items
DeveloperMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"developer"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

SystemMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"system"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

UserMessageobject

Messages sent by an end user, containing prompts or additional context information.

Properties
role"user"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

ToolMessageobject

Messages sent by tools in response to tool calls made by the assistant.

Properties
role"tool"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

tool_call_idstring*required

The ID of the tool call that this message is responding to.

AssistantMessageobject

Messages sent by the model in response to user messages.

Properties
role"assistant"*required
contentunionoptional

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusalstringoptional

The refusal message by the assistant.

tool_callsarrayoptional

Tool calls made by the assistant.

Items
AssistantMessageToolCallFunctionobject

A function tool call made by the assistant.

Properties
type"function"*required
idstring*required

The unique identifier for the tool call.

functionobject*required

The name and arguments of the function called.

Properties
namestring*required

The name of the function called.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning provided by the assistant.

suffix_messagesarrayoptional

A list of messages exchanged in a chat conversation. These will be appended to every prompt sent to this LLM. Useful for setting context or influencing behavior.

Items
DeveloperMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"developer"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

SystemMessageobject

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

Properties
role"system"*required
contentunion*required

Simple content.

Variants
SimpleContentTextstring

Plain text content.

SimpleContentPartsarray

An array of simple content parts.

Items
SimpleContentPartobject

A simple content part.

Properties
type"text"*required
textstring*required

The text content.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

UserMessageobject

Messages sent by an end user, containing prompts or additional context information.

Properties
role"user"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

ToolMessageobject

Messages sent by tools in response to tool calls made by the assistant.

Properties
role"tool"*required
contentunion*required

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

tool_call_idstring*required

The ID of the tool call that this message is responding to.

AssistantMessageobject

Messages sent by the model in response to user messages.

Properties
role"assistant"*required
contentunionoptional

Rich content.

Variants
RichContentTextstring

Plain text content.

RichContentPartsarray

An array of rich content parts.

Items
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.

namestringoptional

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusalstringoptional

The refusal message by the assistant.

tool_callsarrayoptional

Tool calls made by the assistant.

Items
AssistantMessageToolCallFunctionobject

A function tool call made by the assistant.

Properties
type"function"*required
idstring*required

The unique identifier for the tool call.

functionobject*required

The name and arguments of the function called.

Properties
namestring*required

The name of the function called.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning provided by the assistant.

frequency_penaltynumbermin: -2max: 2optional

This setting aims to control the repetition of tokens based on how often they appear in the input. It tries to use less frequently those tokens that appear more in the input, proportional to how frequently they occur. Token penalty scales with the number of occurrences. Negative values will encourage token reuse.

logit_biasrecordoptional

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

Values
numbermin: -100max: 100
max_completion_tokensnumbermin: 0max: 2147483647optional

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

presence_penaltynumbermin: -2max: 2optional

This setting aims to control the presence of tokens in the output. It tries to encourage the model to use tokens that are less present in the input, proportional to their presence in the input. Token presence scales with the number of occurrences. Negative values will encourage more diverse token usage.

stopunionoptional

The assistant will stop when any of the provided strings are generated.

Variants
StopStringstring

Generation will stop when this string is generated.

StopStringsarray

Generation will stop when any of these strings are generated.

Items
StopStringstring
temperaturenumbermin: 0max: 2optional

This setting influences the variety in the model’s responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.

top_pnumbermin: 0max: 1optional

This setting limits the model’s choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model’s responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

max_tokensnumbermin: 0max: 2147483647optional

This sets the upper limit for the number of tokens the model can generate in response. It won’t produce more than this limit. The maximum value is the context length minus the prompt length.

min_pnumbermin: 0max: 1optional

Represents the minimum probability for a token to be considered, relative to the probability of the most likely token. (The value changes depending on the confidence level of the most probable token.) If your Min-P is set to 0.1, that means it will only allow for tokens that are at least 1/10th as probable as the best possible option.

providerobjectoptional

Options for selecting the upstream provider of this model.

Properties
allow_fallbacksbooleanoptional

Whether to allow fallback providers if the preferred provider is unavailable.

require_parametersbooleanoptional

Whether to require that the provider supports all specified parameters.

orderarrayoptional

An ordered list of provider names to use when selecting a provider for this model.

Items
ProviderNamestring
onlyarrayoptional

A list of provider names to restrict selection to when selecting a provider for this model.

Items
ProviderNamestring
ignorearrayoptional

A list of provider names to ignore when selecting a provider for this model.

Items
ProviderNamestring
quantizationsarrayoptional

Specifies the quantizations to allow when selecting providers for this model.

Items
"int4"
"int8"
"fp4"
"fp6"
"fp8"
"fp16"
"bf16"
"fp32"
"unknown"
reasoningobjectoptional

Options for controlling reasoning behavior of the model.

Properties
enabledbooleanoptional

Enables or disables reasoning for supported models.

max_tokensnumbermin: 0max: 2147483647optional

The maximum number of tokens to use for reasoning in a response.

effortenumoptional

Constrains effort on reasoning for supported reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Variants
"none"
"minimal"
"low"
"medium"
"high"
"xhigh"
summary_verbosityenumoptional

Controls the verbosity of the reasoning summary for supported reasoning models.

Variants
"auto"
"concise"
"detailed"
repetition_penaltynumbermin: 0max: 2optional

Helps to reduce the repetition of tokens from the input. A higher value makes the model less likely to repeat tokens, but too high a value can make the output less coherent (often with run-on sentences that lack small words). Token penalty scales based on original token’s probability.

top_anumbermin: 0max: 1optional

Consider only the top tokens with “sufficiently high” probabilities based on the probability of the most likely token. Think of it like a dynamic Top-P. A lower Top-A value focuses the choices based on the highest probability token but with a narrower scope. A higher Top-A value does not necessarily affect the creativity of the output, but rather refines the filtering process based on the maximum probability.

top_knumbermin: 0max: 2147483647optional

This limits the model’s choice of tokens at each step, making it choose from a smaller set. A value of 1 means the model will always pick the most likely next token, leading to predictable results. By default this setting is disabled, making the model to consider all choices.

verbosityenumoptional

Controls the verbosity and length of the model response. Lower values produce more concise responses, while higher values produce more detailed and comprehensive responses.

Variants
"low"
"medium"
"high"
idstring*required

The unique identifier for the Ensemble LLM.

creatednumbermin: 0max: 4294967295*required

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

Objective Artificial Intelligence, Inc.