Unverified50% confidenceFactExact time
When a Gemini API single request's output exceeds the limit, the API returns finish_reason=CONTINUATION along with a continuation_token.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
Unverified在Google Gemini API的响应结构中，finishReason字段用于指示模型为何停止生成内容66% similarUnverifiedGemini 4 Argon achieves 1 million token output through the Gemini API's new Long Decode Continuation feature, which pauses long responses and resumes them in subsequent calls to avoid timeouts.65% similarUnverifiedThe developer wrote a middleware layer to handle Gemini API rate limits and abnormal responses, in order to maintain stable communication between the Gemini API and AutoGen.65% similarUnverifiedIn the Gemini API's continuation protocol, a single streaming request is capped at 65,536 tokens, while a non-streaming direct HTTP request is 32,768.65% similarUnverifiedCalling Gemini in n8n can be done by sending a REST API request via an HTTP Request node, or by using a community-provided Gemini-specific node.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021144API
curl https://kongchang.com/api/v1/knowledge/claims/1021144MCP
get_claim(id=1021144)