On September 10, DeepSeek did something rare: it launched V4.1-Flash and simultaneously put its own flagship V4-Pro on a retirement path. Starting 04:00 UTC on September 14, every deepseek-v4-pro API request will be routed to V4.1-Flash and billed at the new model's rates, until V4.1-Pro ships. The smallest model in the family just pushed the flagship off the stage — that signal matters more than any benchmark score.

Asymmetric architecture: 8B to read, 16B to write

V4.1-Flash is a 552B-parameter MoE built on a new Causal Encoder–Decoder (CED) design: only 8B parameters activate per input token, while output decoding activates 16B. According to the official announcement, new pre-training methods plus larger-scale RL post-training push its benchmark results past flagship models, including V4-Pro.

Third-party analysis (atoms.dev) goes deeper: the 40 Transformer layers split into a 20-layer causal encoder and a 20-layer decoder, and the decoder's global KV cache is no longer derived independently per layer — it is projected from the encoder's final hidden states. The asymmetry maps directly onto agent workloads, where accumulated context, tool returns, and dialogue history make input far larger than output.

KV cache: the cost ceiling for agents

The official announcement states that versus the previous generation, V4.1-Flash's KV cache needs just 1/4 the HBM and 1/8 the SSD storage. The motivation is explicit: in agent tasks, cache-hit charges often account for a large share of total cost.

Details from the model card, as reported by atoms.dev, are more striking: the global KV cache footprint is 890 bytes per token — roughly a quarter of V4-Flash and about 1/437 of the original DeepSeek V1 (independently corroborated by AIBase's coverage). An SWA Bounded Replay mechanism avoids persisting the full sliding-window-attention KV state to SSD, and Compressed Sparse Attention 2 lets attention layers pick among three static modes — Full, Reindex, Reuse — sharing KV data and sparse-attention indices across layers instead of rebuilding them.

Pricing and ecosystem

Pricing keeps the peak/off-peak structure: off-peak rates are 50% of peak, effective 04:00 UTC on September 10. Per atoms.dev's numbers: off-peak uncached input at $0.15 per million tokens, cached input at $0.003, and output at $0.60, with peak rates doubled. On the ecosystem side, official partners WorkBuddy (including CodeBuddy) and OpenCode have announced full support, and the weights plus a technical report are live on Hugging Face. The older V4-Flash and V4-Flash-Vision-Exp are retired, with their model names temporarily routing to V4.1-Flash for compatibility.

Three takeaways

First, "Flash retires Pro" shows the competition shifting from "whose benchmark is higher" to "whose per-token cost is lower" — once a small model matches the flagship on benchmarks, the flagship's remaining value is mostly branding and a bigger parameter story. Second, the asymmetric architecture is purpose-built for the agent era: long contexts, multi-turn calls, and input-heavy traffic mean KV-cache compression hits the cost structure of these workloads directly — more engineering substance than a pure scale narrative. Third, stay sober: "beats the flagship" is currently the official submission; independent analysis confirms the architecture and pricing figures, but for specific benchmark outcomes, test on your own workloads before concluding.

So what: the next round of model competition may be decided not by the parameter sheet but by "the memory bill per token." V4.1-Flash has put that bill on the table — the real question is what V4.1-Pro will use to keep the flagship story alive.