AITOPAI热报
ModelsOfficialSelected

DeepSeek releases V4.1 Flash, replaces V4 Pro

DeepSeek Ships V4.1 Flash GA With Causal-Encoder-Decoder MoE as V4 Pro Retires

官方一手pandaily@[email protected] (Pandaily)
Blog/Media
Read the original
Why we picked it

DeepSeek's new V4.1 Flash model is now available, replacing the V4 Pro version. The pricing for the new model started on September 10, and the transition to Flash is scheduled for September 14.

DeepSeek has released V4.1 Flash for general availability, a 552B MoE model with Causal-Encoder-Decoder architecture and native vision. New Flash pricing started September 10, V4 Pro routes to Flash on September 14, and the app merges modes into one smart mode.

#DeepSeek#V4.1 Flash#MoE#AI models

Keep reading

Recent stories with the same tag or section
ProductsUS vs ChinaSelected07:26
vLLM sets best DeepSeek-V4.1-Flash result on SemiAnalysis AgentX

Matching DeepInfer's performance while beating it on a third-party agentic benchmark suggests vLLM is now a credible production backend for high-throughput DeepSeek serving, not just a research engine. Engineers running agent-heavy inference stacks can use the reproducible blog recipe to benchmark their own deployments against the 954K tokens/s figure. DeepSeek's off-peak pricing makes the revenue-per-GPU-hour number a useful cost baseline for capacity planning.

#vLLM#DeepSeek#AgentX#SemiAnalysis
官方账号vLLM@vllm_projectSource
ModelsBuildersSelected02:02
vLLM Matches DeepInfer on DeepSeek-V4.1-Flash Decode

An open-source inference stack catching up with a frontier lab's in-house engine means teams can serve DeepSeek-V4.1-Flash without relying on the vendor's own tooling. Engineers running self-hosted deployments in Singapore or ASEAN data centres can benchmark vLLM at DEP32 as a direct alternative to DeepInfer's EP64DP64 setup, avoiding engine lock-in while keeping comparable throughput at large batch sizes.

#vLLM#DeepSeek#DeepInfer#inference
官方账号vLLM@vllm_projectSource