DeepSeek V4.1 Flash 1017

Name: DeepSeek V4.1 Flash 1017
Price: 0.15 USD
Author: DeepSeek

DeepSeek🇨🇳 China

active

Compare with other models →

Context window1000K tokens

Input / 1M tokens$0.15

Output / 1M tokens$0.6

Version History

1017snapshotOctober 17, 2026

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of V4.1 Flash, the first DeepSeek model on the CED architecture, with a 552B backbone, 8B/16B asymmetric active parameters and native vision. DeepSeek claims it exceeds V4 Pro on performance, speed and task completion time, but has published no benchmark figures.

Coverage

model releaseDeepSeek

DeepSeek V4.1 Flash 1017 launches with 552B CED backbone, 1M context, $0.15/$0.60 per 1M tokens

DeepSeek has released V4.1 Flash 1017, an October 17, 2026 snapshot built on its new Causal Encoder-Decoder architecture. It uses a 552B-parameter sparse MoE backbone with a 1M-token context window, native image understanding, and pricing of $0.15 input / $0.60 output per 1M tokens on OpenRouter.

October 17, 2026 · 8:35 AM3 min read

DeepSeek DeepSeek V4.1 Flash mixture-of-experts