DeepSeek v4.1 Flash

DeepSeek released DeepSeek-V4.1-Flash, the smallest model in its new architecture family, now live on the DeepSeek API with native multimodal support under the model name deepseek-flash. The 552B-parameter mixture-of-experts model uses a new Causal Encoder–Decoder architecture with just 8B active parameters for input and 16B for output, and its KV cache requires 1/4 the HBM and 1/8 the SSD storage of the previous generation. DeepSeek retired V4-Flash and V4-Flash-Vision-Exp, temporarily routing deepseek-v4-flash and deepseek-v4-flash-vision-exp to V4.1-Flash, and set off-peak API rates at 50% of peak rates.

DeepSeek on X: "🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6" / X DeepSeek on X: "🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6" 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6 🧠 Asymmetric architecture. More intelligence, less cost. 🔹 552B-parameter MoE. 🔹 New Causal Encoder–Decoder architecture: just 8B active parameters for input, 16B for output. 🔹 New pre-training methods + larger-scale RL post-training deliver benchmark results ahead ofShow more 💾 Smaller KV cache. Bigger savings. Compared with the previous generation, V4.1-Flash’s KV cache needs just: 🔹 1/4 the HBM 🔹 1/8 the SSD storage Cache-hit charges often account for a large share of agent costs. Compressing the cache cuts those costs significantly. 3/6 ⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support. Set your model to deepseek-flash. 🔹 V4-Flash & V4-Flash-Vision-Exp are retired. For compatibility, deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to V4.1-Flash. 🔹 Tests byShow more 💰 More efficient architecture. Lower API prices. V4.1-Flash lets us serve more users at a lower cost. We’re passing the savings on to you. 🔹 Peak/off-peak pricing continues to balance demand. 🔹 Off-peak rates are 50% of peak rates. Schedule flexible workloads off-peak toShow more 🌐 Supporting open source. Expanding deployment options. We’ll work closely with the open-source community on V4.1-Flash inference support and explore more deployment options. Planning a large-scale deployment with 2,000 GPUs + a storage cluster? Let’s talk. 🔹 Model:Show more Quick one: DeepSeek V4.1 Flash lands on WorkBuddy/CodeBuddy, co-launched exclusively in China, discounted for two weeks. TokenHub, ima, and Marvis are live day 0 as well. Well played, @deepseek ai 🫡 V4.1 Flash is a really solid model, major gains across text and agentShow more