AITOPAI热报
ModelsOfficialSelected

DeepSeek V4.1 Flash Beta Opens

DeepSeek Opens Time-Boxed V4.1 Flash Beta With Native Multimodal Architecture

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

Priced like V4 Flash but with native multimodal support, this limited beta offers developers a chance to test DeepSeek's new architecture before September 10.

DeepSeek launched a short V4.1 Flash internal beta with new architecture and native multimodal support. The API ID deepseek-v4.1-flash-expires-on-0910 is priced like V4 Flash. It has a cap of 20 concurrent requests and expires around September 10.

Original · pandaily

DeepSeek Opens Time-Boxed V4.1 Flash Beta With Native Multimodal Architecture

DeepSeek has launched a short V4.1 Flash internal beta with a new architecture and native multimodal support. The API ID deepseek-v4.1-flash-expires-on-0910 is priced like V4 Flash, capped at 20 concurrent requests, and set to expire around September 10.

#DeepSeek#V4.1 Flash#multimodal#API#beta

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