The model stopped generating because the content contains a term from a configured blocklist.
Token generation was stopped because the response reached the per-request token limit, but generation is not yet complete. The model response can be continued via a subsequent request using the returned continuation_token.
Request was filtered by an escalation rule. This enum value is not supported in Vertex AI.
The finish reason is unspecified.
The image generation stopped for a reason not otherwise specified.
The generated image may contain prohibited content.
The generated image may be a recitation from a source.
The generated image potentially violates safety policies.
The response candidate content was flagged for using an unsupported language. This enum value is not supported in Vertex AI.
The model generated a function call that is syntactically invalid and can't be parsed.
Finishes due to malformed response.
The model generated the maximum number of tokens allowed by the max_output_tokens parameter.
Request has at least one thought signature missing. This enum value is not supported in Vertex AI.
The model response was blocked by Model Armor. This enum value is not supported in Gemini API.
The model was expected to generate an image, but didn't.
The model stopped generating for a reason not otherwise specified.
The model stopped generating because the content may be prohibited.
Indicates that token generation stopped because the user account is limited or disabled due to Prohibited Use Policy (PUP) violations. This enum value is not supported in Vertex AI.
The model stopped generating because the content may be a recitation from a source.
The model stopped generating because the content potentially violates safety policies. NOTE: When streaming, the content field is empty if content filters block the output.
The model stopped generating because the content may contain sensitive personally identifiable information (SPII).
The model reached a natural stopping point or a configured stop sequence.
The model made too many tool calls in a single request, so the server-side tool loop stopped before the model returned a final answer.
The model generated a function call that is semantically invalid. This can happen, for example, if function calling is not enabled or the generated function is not in the function declaration.
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating.