> ## Content Index
> Fetch the complete content index at: https://www.metatalks.ai/llms.txt
> Use this file to discover other available public pages before exploring further.

# DeepSeek's V4.1-Flash uses a new encoder-decoder design to make long contexts cheaper to run
- URL: https://www.metatalks.ai/deepseek-v4-1-flash-encoder-decoder-long-contexts/
- Published: 2026-09-14T13:09:00.000Z
- Updated: 2026-09-14T13:08:59.000Z
- Author: Al
- Tags: News, Frontier Models, #newswire

**One set of parameters processes the prompt and a larger one generates the answer, and DeepSeek says the design cuts the memory for cached context to a quarter of V4-Flash's.**

On September 10 [DeepSeek released V4.1-Flash](https://www.deepseek.com/en/news/deepseek-v4-1-flash/?ref=metatalks.ai), the smallest model in its new architecture family. The split is 8 billion active parameters for the input and 16 billion for the output. The model handles text and images, accepts up to a million tokens of context and comes with open weights under the MIT license.

DeepSeek puts the [global context cache](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash?ref=metatalks.ai) at 890 bytes per token. For SSD storage it reports a footprint of about an eighth of V4-Flash's, because the model reconstructs the cache for the most recent tokens when needed instead of saving that portion to disk.

Running at maximum reasoning effort, V4.1-Flash scores 40 on the Intelligence Index of [Artificial Analysis](https://artificialanalysis.ai/models/comparisons/deepseek-v4-1-flash-vs-deepseek-v4-pro?ref=metatalks.ai), an independent benchmarking firm, above the 36 of DeepSeek's larger V4 Pro.

The firm estimates an average cost of $0.27 per benchmark task against $0.67 for V4 Pro, even though V4.1-Flash used 89,000 output tokens per task, reasoning included, to V4 Pro's 55,000\. [GLM-5.3-Flash](https://artificialanalysis.ai/models/comparisons/deepseek-v4-1-flash-vs-glm-5-3-flash?ref=metatalks.ai) does slightly better on both counts, at 42 points and $0.25.

At peak hours, DeepSeek charges $0.30 per million uncached input tokens, $1.20 for output and $0.006 for cached input. Off-peak rates are half those amounts.

DeepSeek has also [dropped a plan](https://api-docs.deepseek.com/quick%5Fstart/pricing/?ref=metatalks.ai) to send all V4 Pro requests to the new model from September 14, citing user demand.