Unverified50% confidenceFactExact time
RisenX默认运行在DeepSeek-V4-Flash上，输入/pro命令可在下一轮切换到DeepSeek-V4-Pro随后自动切回，运行/preset max可整个会话使用Pro
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/25/2026
First Seen
Valid until: 11/23/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Pro and V4 Flash are called via API Key with thinking mode enabled, while Qwen3.6 27B is deployed locally.66% similarUnverifiedDeepSeek V4 Flash is a distilled or streamlined version of Pro that significantly reduces inference overhead while retaining core programming capabilities.64% similarUnverifiedIn DeepSeek V4 Flash deployments, DiSpark improved single-user generation speed by 60% to 85%, and the Pro series by 57% to 78%, while maintaining equivalent inference quality63% similarUnverifiedIn the CLI40 command-line operation test, DeepSeek V4 Flash performed best, surpassing V4 Pro.61% similarUnverifiedDeepSeek has launched the experimental multimodal model V4-Flash-Vision-EXP on its API platform, with text capabilities on par with V4 Flash and multimodal agent benchmark performance close to Opus 4.8 levels.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/799632API
curl https://kongchang.com/api/v1/knowledge/claims/799632MCP
get_claim(id=799632)