DeepSeek says its KV cache, which lets the model reuse earlier calculations, needs a quarter of the high-bandwidth memory and an eighth of the SSD storage required by the previous generation's cache.
DeepSeek announced V4.1-Flash on September 10, 2026, with native visual understanding and API access through the deepseek-flash model name. The company says its 552-billion-parameter model activates 8 billion parameters for input processing and 16 billion for output generation. DeepSeek announced lower API prices effective at 04:00 UTC that day, with off-peak rates at half of peak rates. It also said V4-Pro was being phased out: all deepseek-v4-pro requests would route to V4.1-Flash at V4.1-Flash rates from 04:00 UTC on September 14, 2026, until V4.1-Pro launches. SGLang and vLLM both announced launch-day support.
🚀 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
6.1M
21 posts, first seen 16h ago
DeepSeek says its KV cache, which lets the model reuse earlier calculations, needs a quarter of the high-bandwidth memory and an eighth of the SSD storage required by the previous generation's cache.
DeepSeek announced V4.1-Flash on September 10, 2026, with native visual understanding and API access through the deepseek-flash model name. The company says its 552-billion-parameter model activates 8 billion parameters for input processing and 16 billion for output generation. DeepSeek announced lower API prices effective at 04:00 UTC that day, with off-peak rates at half of peak rates. It also said V4-Pro was being phased out: all deepseek-v4-pro requests would route to V4.1-Flash at V4.1-Flash rates from 04:00 UTC on September 14, 2026, until V4.1-Pro launches. SGLang and vLLM both announced launch-day support.
🚀 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
DeepSeek@deepseek_ai💾 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
DeepSeek@deepseek_ai⚡ 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 by…
DeepSeek@deepseek_ai💰 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 to…
DeepSeek@deepseek_ai🌐 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: 🔹…
Zizheng Pan@zizhpanDeepSeek-V4.1-Flash is now publicly available on App, Web, and API. Our first flagship model with native multimodal support. Faster. More capable. Lower price. Open weights as usual.
Zain@zainhasoh wow have not seen this before for any model... this complicates things > "DeepSeek-V4.1-Flash supports a continuously controllable reasoning effort from 1 to 100." reasoning_effort = [1 to 100]
Based on 123 sentiment-bearing replies from 110 accounts across 10 conversations.
Based on 123 sentiment-bearing replies from 110 accounts across 10 conversations.
DeepSeek@deepseek_ai🧠 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 of…
DeepSeek@deepseek_ai💾 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
DeepSeek@deepseek_ai⚡ 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 by…
DeepSeek@deepseek_ai💰 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 to…
DeepSeek@deepseek_ai🌐 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: 🔹…
#1
#1