New Deepseek model V4.1-Flash cuts memory needs for AI agents
DeepSeek released V4.1-Flash, a 552B-parameter open-weight model cutting KV cache needs to a quarter of its predecessor for cheaper million-token AI agents.
DeepSeek released V4.1-Flash, a multimodal model with 552 billion total parameters and 1 million-token context, trained from scratch on 45 trillion tokens of text and images. The model reduces KV cache footprint to about a quarter of DeepSeek-V4-Flash in fast GPU memory and one-eighth offloaded, and 437x smaller per token than DeepSeek-V1, via an encoder/decoder split, 8-16B active parameters per token, and FP4 cache storage. It scores 74.2% on DeepSWE v1.1, narrowly beating Anthropic Opus 5 and OpenAI GPT-5.6 Sol, with gains attributed to data and RL scaling rather than new algorithms. Weights are on Hugging Face under MIT license, also served via API at V4-Flash prices.
- 552B-parameter model with 1M-token context, trained on 45T tokens
- KV cache cut to ~1/4 of predecessor in GPU memory via FP4 and encoder/decoder split
- 74.2% on DeepSWE v1.1, narrowly beating Opus 5 and GPT-5.6 Sol
- Released under MIT license on Hugging Face; also available via API
- Gaps remain vs. closed frontier models on expert tasks and complex image understanding
- Products
- Hugging Face
- Organizations
- CITIC Securities
- Countries
- China
From the original article
3 min read at the-decoder.com
Deepseek releases V4. 1-Flash, a multimodal model with 552 billion parameters that cuts KV cache memory to a quarter of its predecessor. On the DeepSWE coding benchmark, it narrowly beats Opus 5 and GPT-5.
By Jonathan Kemper · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.