Check out the new Gemini API Cookbook and our community forum.

google.ai.generativelanguage.Candidate.FinishReason

View source on GitHub

Defines the reason why the model stopped generating tokens.

View aliases

Main aliases

`google.ai.generativelanguage_v1beta.Candidate.FinishReason`

Values
`FINISH_REASON_UNSPECIFIED`	`0` Default value. This value is unused.
`STOP`	`1` Natural stop point of the model or provided stop sequence.
`MAX_TOKENS`	`2` The maximum number of tokens as specified in the request was reached.
`SAFETY`	`3` The candidate content was flagged for safety reasons.
`RECITATION`	`4` The candidate content was flagged for recitation reasons.
`OTHER`	`5` Unknown reason.

Class Variables
FINISH_REASON_UNSPECIFIED	`<FinishReason.FINISH_REASON_UNSPECIFIED: 0>`
MAX_TOKENS	`<FinishReason.MAX_TOKENS: 2>`
OTHER	`<FinishReason.OTHER: 5>`
RECITATION	`<FinishReason.RECITATION: 4>`
SAFETY	`<FinishReason.SAFETY: 3>`
STOP	`<FinishReason.STOP: 1>`

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2023-12-13 UTC.