DeepSeek-V4.1-Flash

DeepSeek llm

Causal encoder-decoder MoE (8B active for prefill, 16B for decode) with native vision; replaces V4-Flash and V4-Pro on the DeepSeek API.

overall ⌄

59.2

36 of 125 ranked

price · $/M tokens

0.3 / 1.2

in / out, as of 2026-07-25

to run it yourself ⌄

331 GB

minimum · 1.3 TB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
GPQA90.9 —
HLE36.8 —

Cheaper, and at least as good

On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.

Claude Haiku 5.5 Anthropic$0.00060overall 65.3
Qwen3.8-Flash-Next Alibaba$0.00062overall 61.2
DeepSeek V4-Pro DeepSeek$0.00130overall 65.6
MiniMax M3 MiniMax$0.00150overall 61.8

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

orgDeepSeek
released2026-09-10
params552B-A16B
licensemit
hf iddeepseek-ai/DeepSeek-V4.1-Flash