GenMagic logoGenMagic
Sign in

DeepSeek V4.1 Flash vs DeepSeek V4.1 Flash 1017

DeepSeek against DeepSeek, the same lab's consecutive models. Prices, scores and speed below are live.

  • DeepSeek V4.1 Flash costs 70% less on blended price ($0.24 against $0.79 per 1M tokens, 3 input to 1 output).
  • DeepSeek V4.1 Flash scores higher on the Artificial Analysis Intelligence Index: 39.5 against 28.5.
  • On the 12 benchmarks both have scores on, DeepSeek V4.1 Flash leads on 3 and DeepSeek V4.1 Flash 1017 on 8, with 1 tied.
  • Both read up to 1M tokens of context.
  • DeepSeek V4.1 Flash 1017 is newer: listed Oct 17, 2026, against Sep 10, 2026.
Run both on your promptDeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017

Side by side

DeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017
LabDeepSeekDeepSeek
ListedSep 10, 2026Oct 17, 2026
Input per 1M tokens$0.068$0.45
Output per 1M tokens$0.75$1.80
Cached input per 1M$0.009$0.009
Blended (3:1) per 1M$0.24$0.79
Context window1M1M
Max output944K393K
Knowledge cutoff--
Intelligence index39.528.5
Coding index--
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkDeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017
AIME98.3%Epoch AI99.4%Epoch AI
APEX-Agents39.5%Epoch AI69.8%Epoch AI
ARC-AGI-194.5%Epoch AI94.5%Epoch AI
ARC-AGI-272.9%Epoch AI78.1%Epoch AI
Chess Puzzles48%Epoch AI46%Epoch AI
FrontierMath Tier 4 (v2)26.8%Epoch AI46.3%Epoch AI
FrontierMath Tiers 1-3 (v2)67.4%Epoch AI71.2%Epoch AI
GPQA Diamond89.1%Artificial Analysis and OpenRouter90.1%Artificial Analysis and OpenRouter
Mystery Game Puzzles43%Epoch AI49%Epoch AI
SciCode51.9%Epoch AI55.9%Epoch AI
SimpleQA Verified42.9%Epoch AI42.5%Epoch AI
tau-bench (Airline)75.1%Artificial Analysis and OpenRouter72.3%Artificial Analysis and OpenRouter

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See DeepSeek models, DeepSeek models, every LLM's price and our sources.