Skip to main content

DeepSeek V4.1 Flash vs DeepSeek-V4-Flash (Preview)

SpecDeepSeek V4.1 FlashDeepSeek-V4-Flash (Preview)
Respan Index52.5 (#37)32.3 (#83)
Blended price per 1M$0.089$0.056
Context window1M1M
Input / output per 1M$0.051 / $0.203$0.028 / $0.14
Max output384K-
Inputtext, visiontext
Released2026-09-102026-04-24

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryDeepSeek V4.1 FlashDeepSeek-V4-Flash (Preview)
Coding43.7 DeepSeek V4.1 Flash13.5 DeepSeek-V4-Flash (Preview)
Agents58.4 DeepSeek V4.1 Flash43.2 DeepSeek-V4-Flash (Preview)
Reasoning55.5 DeepSeek V4.1 Flash31.8 DeepSeek-V4-Flash (Preview)
Knowledge & language44.5 DeepSeek V4.1 Flash23.6 DeepSeek-V4-Flash (Preview)
Human preference57.5 DeepSeek V4.1 Flash51.8 DeepSeek-V4-Flash (Preview)

How the Respan Index works

Benchmarks both report

DeepSeek V4.1 Flash leads on 4 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V4.1 FlashDeepSeek-V4-Flash (Preview)
LMArena Elo14751439
LMArena WebDev (LMArena)16591431
GPQA Diamond90.9%88.1%
SimpleBench (SimpleBench)66.7%46.3%

FAQ

Is DeepSeek V4.1 Flash better than DeepSeek-V4-Flash (Preview)?

DeepSeek V4.1 Flash scores 52.5 on the Respan Index (#37), ahead of DeepSeek-V4-Flash (Preview) at 32.3 (#83). DeepSeek V4.1 Flash leads on 4 of the 4 benchmarks both report.

Which is cheaper, DeepSeek V4.1 Flash or DeepSeek-V4-Flash (Preview)?

DeepSeek V4.1 Flash lists at $0.051 input and $0.203 output per 1M tokens; DeepSeek-V4-Flash (Preview) at $0.028 and $0.14. DeepSeek-V4-Flash (Preview) is 1.6x cheaper per token at list price.

Which has the larger context window?

Both accept 1M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.