google-genai-kotlin/com.google.genai.kotlin.types/Candidate

Candidate

@Serializable

data class Candidate(val content: Content? = null, val citationMetadata: CitationMetadata? = null, val finishMessage: String? = null, val tokenCount: Int? = null, val finishReason: FinishReason? = null, val groundingMetadata: GroundingMetadata? = null, val avgLogprobs: Double? = null, val index: Int? = null, val logprobsResult: LogprobsResult? = null, val safetyRatings: List<SafetyRating>? = null, val urlContextMetadata: UrlContextMetadata? = null)

A response candidate generated from the model.

Constructors

Candidate

constructor(content: Content? = null, citationMetadata: CitationMetadata? = null, finishMessage: String? = null, tokenCount: Int? = null, finishReason: FinishReason? = null, groundingMetadata: GroundingMetadata? = null, avgLogprobs: Double? = null, index: Int? = null, logprobsResult: LogprobsResult? = null, safetyRatings: List<SafetyRating>? = null, urlContextMetadata: UrlContextMetadata? = null)

Properties

avgLogprobs

val avgLogprobs: Double? = null

Output only. The average log probability of the tokens in this candidate. This is a length-normalized score that can be used to compare the quality of candidates of different lengths. A higher average log probability suggests a more confident and coherent response.

citationMetadata

val citationMetadata: CitationMetadata? = null

Source attribution of the generated content.

content

val content: Content? = null

Contains the multi-part content of the response.

finishMessage

val finishMessage: String? = null

Describes the reason the model stopped generating tokens.

finishReason

val finishReason: FinishReason? = null

The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

groundingMetadata

val groundingMetadata: GroundingMetadata? = null

Output only. Metadata returned when grounding is enabled. It contains the sources used to ground the generated content.

index

val index: Int? = null

Output only. The 0-based index of this candidate in the list of generated responses. This is useful for distinguishing between multiple candidates when candidate_count 1.

logprobsResult

val logprobsResult: LogprobsResult? = null

Output only. The detailed log probability information for the tokens in this candidate. This is useful for debugging, understanding model uncertainty, and identifying potential "hallucinations".

safetyRatings

val safetyRatings: List<SafetyRating>? = null

Output only. A list of ratings for the safety of a response candidate. There is at most one rating per category.

tokenCount

val tokenCount: Int? = null

Number of tokens for this candidate.

urlContextMetadata

val urlContextMetadata: UrlContextMetadata? = null

Output only. Metadata returned when the model uses the url_context tool to get information from a user-provided URL.