Unverified50% confidenceBenchmarkExact time
According to Artificial Analysis data, DeepSeek V4.1 Flash can reach 1286 tokens per second via Lithos AI, and Base 10 provides an inference speed of 845 tokens per second.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/28/2026
First Seen
Valid until: 11/11/2026
Sources
Related Entities
Related Claims
UnverifiedTesters indicate that DeepSeek V4 Flash can handle approximately 90% of their daily work, especially on intelligent agent tasks.74% similarUnverifiedDeepSeek V4.1 Flash (the October 17 update referred to as 1017) and MiniMax M3.1 Flash official version were compared and tested on real archives exceeding 100,000 tokens, the official APIs, and the same AI Max hardware.72% similarVerifiedArtificial Analysis evaluation shows DeepSeek V4.1 Flash scored 40 on the Intelligence Index, surpassing V4 Pro to become DeepSeek's new flagship, featuring native multimodal input, 8B activated parameters on input and 16B on output, released under the MIT license.72% similarVerifiedCompared with the previous version, DeepSeek V4.1 Flash 1017 completes tasks faster and produces shorter output.71% similarUnverifiedIn the receipt recognition task, DeepSeek V4.1 Flash was twice as fast as Haiku 5.5.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109669API
curl https://kongchang.com/api/v1/knowledge/claims/1109669MCP
get_claim(id=1109669)