The maximum number of tokens as specified in the request was reached.
Other
All other reasons that stopped the token generation
Recitation
The token generation was stopped as the response was flagged for
unauthorized citations.
Safety
The token generation was stopped as the response was flagged for safety
reasons. NOTE: When streaming the Candidate.content will be empty if
content filters blocked the output.
Stop
Natural stop point of the model or provided stop sequence.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-03-21 UTC."],[[["This webpage provides documentation for the `Candidate.Types.FinishReason` enum within the Google Cloud AI Platform V1 API, detailing the various reasons a model may stop generating tokens."],["The latest version of this documentation is for version 3.22.0, with links available to documentation for various previous versions, all the way back to version 1.0.0."],["The `Candidate.Types.FinishReason` enum includes values like `MaxTokens`, `Other`, `Recitation`, `Safety`, `Stop`, and `Unspecified`, each describing a specific reason for token generation termination."],["Each version listed on the page links to the specific documentation for the `Candidate.Types.FinishReason` within that version of the API, allowing users to see how the enum has changed over time."],["The documentation specifies that when `Safety` is the finish reason, the `Candidate.content` will be empty if content filters blocked the output."]]],[]]
