Request Headers

authorizationstringoptional

The authorization token (optional).

Request Path

authorstring*required

The author of the App.

idstring*required

The unique identifier of the App.

Request Query

metadatabooleanoptional

Whether to include metadata in the response. If false, all other query fields are ignored.

mebooleanoptional

Whether to only return the user's own metadata statistics. If true, authorization is required.

fromstringoptional

An RFC 3339 start date to filter metadata statistics by.

tostringoptional

An RFC 3339 end date to filter metadata statistics by.

Response Body

authorstring*required

The author of the App.

idstring*required

The unique identifier of the App.

versionnumber*required

The version of the App.

descriptionstring*required

The description of the App.

inputmap<string, object>*required

A map defining the inputs for the App.

Map Value Variants
Array Propertyobject
Properties
type"array"*required
descriptionstringoptional
itemsmap<string, object>*required
Map Value Variants
String Propertyobject
Properties
type"string"*required
descriptionstringoptional
enumarrayoptional
Items
Valuestring
Number Propertyobject
Properties
type"number"*required
descriptionstringoptional
Integer Propertyobject
Properties
type"integer"*required
descriptionstringoptional
Boolean Propertyobject
Properties
type"boolean"*required
descriptionstringoptional
String Propertyobject
Properties
type"string"*required
descriptionstringoptional
enumarrayoptional
Items
Valuestring
Number Propertyobject
Properties
type"number"*required
descriptionstringoptional
Integer Propertyobject
Properties
type"integer"*required
descriptionstringoptional
Boolean Propertyobject
Properties
type"boolean"*required
descriptionstringoptional
stepsenum*required

The steps which the App will execute in succession, providing the output of previous steps to the next.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Multichat Stepobject

The step will be a Multichat Completion

Properties
messagesenum*required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

refusalenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

tool_callsenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Tool Callobject
Properties
idenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

functionenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valueobject

The direct value.

Properties
nameenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

argumentsenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idenum*required

The ID of the Chat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Chat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idenum*required

The ID of the Score Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Score Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idenum*required

The ID of the Multichat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Multichat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

modelenum*required

The Multichat Model to use for the Multichat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Multichat Model IDstring

The base62 22-character unique identifier for the Multichat Model.

Multichat Model Objectobject

The provided Multichat Model object.

Properties
modelsarraymin: 1*required

The LLMs which make up the Model.

Items
Score LLMobject

An LLM which is part of the Model.

Properties
modelstring*required

Model ID used to generate the response.

weightenum*required

The weight of the model, which determines its influence on the Confidence Score. Must match the weight strategy of the parent Model.

Variants
Static Weightobject

A static weight value.

Properties
type"static"*required
weightnumber*required

The static weight value.

Training Table Weightobject

A dynamic weight value based on training table data.

Properties
type"training_table"*required
base_weightnumber*required

The base weight value, uninfluenced by training table data.

min_weightnumber*required

The minimum weight value. A model that never matches the correct answer will have this weight.

max_weightnumber*required

The maximum weight value. A model that always matches the correct answer will have this weight.

modeenum*required

The output mode of the model, which determines how it's constrained to select from provided choices.

Variants
Instruction"instruction"

The model is instructed to output a response key.

JSON Schema"json_schema"

The model is provided a schema to output a response key.

Tool Call"tool_call"

The model is made to call a tool with a response key as an argument.

synthetic_reasoningbooleanoptional

For non-reasoning LLMs, whether to enable synthetic reasoning to make the selection more thought-out. Requires output_mode of "json_schema" or "tool_call".

top_logprobsnumbermin: 0max: 20optional

If set, and the LLM supports it, turns the vote into a probability distribution. This increases score quality by allowing the LLM to express uncertainty.

messagesarrayoptional

A list of messages to prepend to every request to this LLM. Useful for setting context or influencing behavior.

Items
Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
refusalstringoptional
tool_callsarrayoptional
Items
Tool Callobject
Properties
idstring*required
functionobject*required
Properties
namestring*required
argumentsstring*required
type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idstring*required
Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idstring*required

The ID of the Chat Completion.

choice_indexnumber*required

The index of the choice in the Chat Completion.

namestringoptional
Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idstring*required

The ID of the Score Completion.

choice_indexnumber*required

The index of the choice in the Score Completion.

namestringoptional
Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idstring*required

The ID of the Multichat Completion.

choice_indexnumber*required

The index of the choice in the Multichat Completion.

namestringoptional
suffix_messagesarrayoptional

A list of messages to append to every request to this LLM. Useful for setting context or influencing behavior.

Items
Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
refusalstringoptional
tool_callsarrayoptional
Items
Tool Callobject
Properties
idstring*required
functionobject*required
Properties
namestring*required
argumentsstring*required
type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idstring*required
Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idstring*required

The ID of the Chat Completion.

choice_indexnumber*required

The index of the choice in the Chat Completion.

namestringoptional
Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idstring*required

The ID of the Score Completion.

choice_indexnumber*required

The index of the choice in the Score Completion.

namestringoptional
Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idstring*required

The ID of the Multichat Completion.

choice_indexnumber*required

The index of the choice in the Multichat Completion.

namestringoptional
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_biasmap<string, number>optional

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.

max_completion_tokensnumbermin: 1optional

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.

stopenumoptional

Stop generation immediately if the model encounters any token specified in the stop array.

Variants
Stop Stringstring
Stop Arrayarray
Items
Stop Stringstring
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: 1optional

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

OpenRouter provider preferences.

Properties
orderarrayoptional

List of provider slugs to try in order.

Items
Provider Slugstring
allow_fallbacksbooleanoptional

Whether to allow backup providers when the primary is unavailable.

require_parametersbooleanoptional

Only use providers that support all parameters in your request.

data_collectionenumoptional

Control whether to use providers that may store data.

Variants
Allow"allow"
Deny"deny"
onlyarrayoptional

List of provider slugs to allow for this request.

Items
Provider Slugstring
ignorearrayoptional

List of provider slugs to skip for this request.

Items
Provider Slugstring
quantizationsarrayoptional

List of quantization levels to filter by.

Items
Quantization Levelstring
sortstringoptional

Sort providers by price or throughput.

reasoningobjectoptional

OpenRouter reasoning configuration.

Properties
max_tokensnumbermin: 1optional

An upper bound for the number of tokens that can be generated for reasoning.

effortenumoptional

Constrains effort on reasoning for some reasoning models.

Variants
Minimal"minimal"
Low"low"
Medium"medium"
High"high"
enabledbooleanoptional

Whether reasoning is enabled for this request.

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: 1optional

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"low"
Medium"medium"
High"high"
modelsarrayoptional

Fallback models. Will be tried in order if the first one fails.

Items
Model IDstring
weightenum*required

The weight strategy for the Model, which determines how the Confidence Score is calculated.

Variants
Static Weightobject

Each LLM has a fixed weight.

Properties
type"static"*required
Training Table Weightobject

Each LLM has a dynamic weight based on training table data.

Properties
type"training_table"*required
embeddingsobject*required
Properties
modelstring*required

The embedding model used to compute prompt embeddings for a training table vector search.

max_tokensnumber*required

The maximum number of input tokens that the embedding model can process into a single embedding.

providerobjectoptional

OpenRouter provider preferences.

Properties
orderarrayoptional

List of provider slugs to try in order.

Items
Provider Slugstring
allow_fallbacksbooleanoptional

Whether to allow backup providers when the primary is unavailable.

require_parametersbooleanoptional

Only use providers that support all parameters in your request.

data_collectionenumoptional

Control whether to use providers that may store data.

Variants
Allow"allow"
Deny"deny"
onlyarrayoptional

List of provider slugs to allow for this request.

Items
Provider Slugstring
ignorearrayoptional

List of provider slugs to skip for this request.

Items
Provider Slugstring
quantizationsarrayoptional

List of quantization levels to filter by.

Items
Quantization Levelstring
sortstringoptional

Sort providers by price or throughput.

topnumbermin: 1*required

The number of most similar training table entries to consider when computing the dynamic weight.

response_formatenumoptional

An object specifying the format that the model must output.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Response Formatobject

Responses will have no specific format.

Properties
type"text"*required
JSON Object Response Formatobject

Responses will be JSON Objects.

Properties
type"json_object"*required
JSON Schema Response Formatobject

Responses will adhere to the provided JSON Schema.

Properties
type"json_schema"*required
json_schemaenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valueobject

The direct value.

Properties
nameenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

descriptionenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

strictenumoptional

Whether to strictly enforce the schema. If true, the model will only output properties defined in the schema. If false, the model may output additional properties.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valueboolean

The direct value.

schemaenumoptional

The JSON Schema object defining the expected structure.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuejson_value

The direct value.

Score Stepobject

The step will be a Score Completion

Properties
messagesenum*required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

refusalenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

tool_callsenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Tool Callobject
Properties
idenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

functionenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valueobject

The direct value.

Properties
nameenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

argumentsenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Text Contentstring
Array Contentarray
Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idenum*required
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idenum*required

The ID of the Chat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Chat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idenum*required

The ID of the Score Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Score Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idenum*required

The ID of the Multichat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

choice_indexenum*required

The index of the choice in the Multichat Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuenumber

The direct value.

nameenumoptional
Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuestring

The direct value.

modelenum*required

The Score Model to use for the Score Completion.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Score Model IDstring

The base62 22-character unique identifier for the Score Model.

Score Model Objectobject

The provided Score Model object.

Properties
modelsarraymin: 1*required

The LLMs which make up the Model.

Items
Score LLMobject

An LLM which is part of the Model.

Properties
modelstring*required

Model ID used to generate the response.

weightenum*required

The weight of the model, which determines its influence on the Confidence Score. Must match the weight strategy of the parent Model.

Variants
Static Weightobject

A static weight value.

Properties
type"static"*required
weightnumber*required

The static weight value.

Training Table Weightobject

A dynamic weight value based on training table data.

Properties
type"training_table"*required
base_weightnumber*required

The base weight value, uninfluenced by training table data.

min_weightnumber*required

The minimum weight value. A model that never matches the correct answer will have this weight.

max_weightnumber*required

The maximum weight value. A model that always matches the correct answer will have this weight.

modeenum*required

The output mode of the model, which determines how it's constrained to select from provided choices.

Variants
Instruction"instruction"

The model is instructed to output a response key.

JSON Schema"json_schema"

The model is provided a schema to output a response key.

Tool Call"tool_call"

The model is made to call a tool with a response key as an argument.

synthetic_reasoningbooleanoptional

For non-reasoning LLMs, whether to enable synthetic reasoning to make the selection more thought-out. Requires output_mode of "json_schema" or "tool_call".

top_logprobsnumbermin: 0max: 20optional

If set, and the LLM supports it, turns the vote into a probability distribution. This increases score quality by allowing the LLM to express uncertainty.

messagesarrayoptional

A list of messages to prepend to every request to this LLM. Useful for setting context or influencing behavior.

Items
Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
refusalstringoptional
tool_callsarrayoptional
Items
Tool Callobject
Properties
idstring*required
functionobject*required
Properties
namestring*required
argumentsstring*required
type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idstring*required
Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idstring*required

The ID of the Chat Completion.

choice_indexnumber*required

The index of the choice in the Chat Completion.

namestringoptional
Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idstring*required

The ID of the Score Completion.

choice_indexnumber*required

The index of the choice in the Score Completion.

namestringoptional
Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idstring*required

The ID of the Multichat Completion.

choice_indexnumber*required

The index of the choice in the Multichat Completion.

namestringoptional
suffix_messagesarrayoptional

A list of messages to append to every request to this LLM. Useful for setting context or influencing behavior.

Items
Developer Messageobject
Properties
role"developer"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
System Messageobject
Properties
role"system"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
namestringoptional
User Messageobject
Properties
role"user"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
Assistant Messageobject
Properties
role"assistant"*required
contentenumoptional

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
namestringoptional
refusalstringoptional
tool_callsarrayoptional
Items
Tool Callobject
Properties
idstring*required
functionobject*required
Properties
namestring*required
argumentsstring*required
type"function"*required
Tool Messageobject
Properties
role"tool"*required
contentenum*required

The content of the message.

Variants
Text Contentstring
Array Contentarray
Items
Text Content Partobject
Properties
type"text"*required
textstring*required
Image Content Partobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
detailenumoptional
Variants
Auto"auto"
Low"low"
High"high"
Audio Content Partobject
Properties
type"audio_url"*required
input_audioobject*required
Properties
datastring*required
formatenum*required
Variants
WAV"wav"
MP3"mp3"
Video Content Partobject
Properties
type"input_video"*required
video_urlobject*required
Properties
urlstring*required
File Content Partobject
Properties
type"file"*required
fileobject*required
Properties
file_datastringoptional
file_idstringoptional
filenamestringoptional
tool_call_idstring*required
Chat Completion Messageobject

Use a Chat Completion from a previous response. Converts into an Assistant Message.

Properties
role"chat_completion"*required
idstring*required

The ID of the Chat Completion.

choice_indexnumber*required

The index of the choice in the Chat Completion.

namestringoptional
Score Completion Messageobject

Use a Score Completion from a previous response. Converts into an Assistant Message.

Properties
role"score_completion"*required
idstring*required

The ID of the Score Completion.

choice_indexnumber*required

The index of the choice in the Score Completion.

namestringoptional
Multichat Completion Messageobject

Use a Multichat Completion from a previous response. Converts into an Assistant Message.

Properties
role"multichat_completion"*required
idstring*required

The ID of the Multichat Completion.

choice_indexnumber*required

The index of the choice in the Multichat Completion.

namestringoptional
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_biasmap<string, number>optional

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.

max_completion_tokensnumbermin: 1optional

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.

stopenumoptional

Stop generation immediately if the model encounters any token specified in the stop array.

Variants
Stop Stringstring
Stop Arrayarray
Items
Stop Stringstring
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: 1optional

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

OpenRouter provider preferences.

Properties
orderarrayoptional

List of provider slugs to try in order.

Items
Provider Slugstring
allow_fallbacksbooleanoptional

Whether to allow backup providers when the primary is unavailable.

require_parametersbooleanoptional

Only use providers that support all parameters in your request.

data_collectionenumoptional

Control whether to use providers that may store data.

Variants
Allow"allow"
Deny"deny"
onlyarrayoptional

List of provider slugs to allow for this request.

Items
Provider Slugstring
ignorearrayoptional

List of provider slugs to skip for this request.

Items
Provider Slugstring
quantizationsarrayoptional

List of quantization levels to filter by.

Items
Quantization Levelstring
sortstringoptional

Sort providers by price or throughput.

reasoningobjectoptional

OpenRouter reasoning configuration.

Properties
max_tokensnumbermin: 1optional

An upper bound for the number of tokens that can be generated for reasoning.

effortenumoptional

Constrains effort on reasoning for some reasoning models.

Variants
Minimal"minimal"
Low"low"
Medium"medium"
High"high"
enabledbooleanoptional

Whether reasoning is enabled for this request.

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: 1optional

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"low"
Medium"medium"
High"high"
modelsarrayoptional

Fallback models. Will be tried in order if the first one fails.

Items
Model IDstring
weightenum*required

The weight strategy for the Model, which determines how the Confidence Score is calculated.

Variants
Static Weightobject

Each LLM has a fixed weight.

Properties
type"static"*required
Training Table Weightobject

Each LLM has a dynamic weight based on training table data.

Properties
type"training_table"*required
embeddingsobject*required
Properties
modelstring*required

The embedding model used to compute prompt embeddings for a training table vector search.

max_tokensnumber*required

The maximum number of input tokens that the embedding model can process into a single embedding.

providerobjectoptional

OpenRouter provider preferences.

Properties
orderarrayoptional

List of provider slugs to try in order.

Items
Provider Slugstring
allow_fallbacksbooleanoptional

Whether to allow backup providers when the primary is unavailable.

require_parametersbooleanoptional

Only use providers that support all parameters in your request.

data_collectionenumoptional

Control whether to use providers that may store data.

Variants
Allow"allow"
Deny"deny"
onlyarrayoptional

List of provider slugs to allow for this request.

Items
Provider Slugstring
ignorearrayoptional

List of provider slugs to skip for this request.

Items
Provider Slugstring
quantizationsarrayoptional

List of quantization levels to filter by.

Items
Quantization Levelstring
sortstringoptional

Sort providers by price or throughput.

topnumbermin: 1*required

The number of most similar training table entries to consider when computing the dynamic weight.

choicesenum*required

The choices which the Score Model will Score.

Variants
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type.

Valuearray

The direct value.

Items
Expressionobject

An expression to be evaluated.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the other variant type or an array of the other variant type.

Text Choicestring

A text choice to be scored.

Message Choiceobject

A completion choice message to be scored.

Properties
contentstringoptional

The content of the message generated by the model.

refusalstringoptional

The refusal information if the model refused to generate a message.

role"assistant"*required

The role of the message, which is always assistant for model-generated messages.

annotationsarrayoptional

The annotations added by the model in this message.

Items
Annotationobject
Properties
type"url_citation"*required
url_citationobject*required
Properties
end_indexnumber*required

The end index of the citation in the message content.

start_indexnumber*required

The start index of the citation in the message content.

titlestring*required

The title of the cited webpage.

urlstring*required

The URL of the cited webpage.

audioobjectoptional

The audio generated by the model in this message.

Properties
idstring*required
datastring*required
expires_atnumber*required
transcriptstring*required
tool_callsarrayoptional

The tool calls made by the model in this delta.

Items
idstring*required

The tool call ID.

type"function"*required
functionobject*required
Properties
namestring*required

The name of the function being called.

argumentsstring*required

The arguments passed to the function.

reasoningstringoptional

The reasoning text generated by the model in this message.

imagesarrayoptional

The images generated by the model in this message.

Items
Imageobject
Properties
type"image_url"*required
image_urlobject*required
Properties
urlstring*required
Chat Completion Choiceobject

A chat completion choice to be scored.

Properties
type"chat_completion"*required
idstring*required

The unique identifier for the chat completion.

choice_indexnumber*required

The index of the choice in the chat completion.

Score Completion Choiceobject

A score completion choice to be scored.

Properties
type"score_completion"*required
idstring*required

The unique identifier for the score completion.

choice_indexnumber*required

The index of the choice in the score completion.

Multichat Completion Choiceobject

A multichat completion choice to be scored.

Properties
type"multichat_completion"*required
idstring*required

The unique identifier for the multichat completion.

choice_indexnumber*required

The index of the choice in the multichat completion.

outputobject

An expression to be evaluated. This will be the output of the App.

Properties
$jsonpathstring

A JSONPath expression that evaluates to the App's output, given the input and the outputs of all steps.

createdstringoptional

The RFC 3339 timestamp when the App was published

requestsnumberoptional

The number of completion requests made by the App

completion_tokensnumberoptional

The number of completion tokens generated by the App

prompt_tokensnumberoptional

The number of prompt tokens processed by the App

total_costnumberoptional

The total cost of completions generated by the App, in Credits

Objective Artificial Intelligence, Inc.