Verified80% confidenceFactTime unknown
Early versions of the Kimi series of models supported a context input of 2 million Chinese characters.
6
Sources
80%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedKimi K2.5是大规模混合专家（MoE）架构的语言模型69% similarVerifiedMoonshot AI's Kimi series models are known for their long-context capability, which supports extremely long text input.65% similarUnverifiedKimi智能助手最初以支持20万字超长文本输入为卖点切入市场62% similarUnverifiedKimi can handle long texts of hundreds of thousands of characters, but the video complains that this capability causes users to be frequently asked to produce summaries, creating the side effect of an accelerated work pace.59% similarUnverifiedKimi K3 comes from Moonshot AI and has a differentiated focus on long-text processing.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/3977API
curl https://kongchang.com/api/v1/knowledge/claims/3977MCP
get_claim(id=3977)