Unverified50% confidenceFactExact time
Gemini 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedArtificial Analysis used the Gemini API's long-output continuation feature during testing, enabling inference of up to 1 million output tokens and avoiding request timeouts.70% similarVerifiedGemini 4 Argon claims to support an output capacity of 1 million tokens.70% similarUnverifiedGemini 3.5 Transcribe can automatically remove false starts and filler words, and identifies self-corrections to retain only the final result.68% similarVerifiedGemini 4 Argon's maximum output has been increased from 64,000 tokens to 1 million (referring to the output limit, not the context window)68% similarUnverifiedGemini SDK提供了CountTokens方法，允许开发者在发送请求前精确计算输入的Token数量68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016885API
curl https://kongchang.com/api/v1/knowledge/claims/1016885MCP
get_claim(id=1016885)