Skip to main content
Launching the open-source gateway

DeepSeek V4.1 Flash vs Hy3

SpecDeepSeek V4.1 FlashHy3
Respan Index52.0 (#28)39.5 (#63)
Blended price per 1M$0.071$0.231
Context window1M256K
Input / output per 1M$0.045 / $0.15$0.132 / $0.528
Max output384K-
Inputtext, visiontext
Released2026-09-102026-07-06

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 FlashHy3
Coding39.7 DeepSeek V4.1 Flash16.3 Hy3
Agents60.0 DeepSeek V4.1 Flash51.3 Hy3
Reasoning56.0 DeepSeek V4.1 Flash43.3 Hy3
Knowledge & language44.5 DeepSeek V4.1 Flash37.7* Hy3
Human preference57.6 DeepSeek V4.1 Flash53.4 Hy3

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

DeepSeek V4.1 Flash leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V4.1 FlashHy3
GPQA Diamond90.9%90.4%
LMArena Agent (LMArena)0.0267-0.0732
LMArena Elo14761455
LMArena WebDev (LMArena)16651505
Terminal-Bench 2.190.6%71.7%

FAQ

Is DeepSeek V4.1 Flash better than Hy3?

DeepSeek V4.1 Flash scores 52.0 on the Respan Index (#28), ahead of Hy3 at 39.5 (#63). DeepSeek V4.1 Flash leads on 5 of the 5 benchmarks both report.

Which is cheaper, DeepSeek V4.1 Flash or Hy3?

DeepSeek V4.1 Flash lists at $0.045 input and $0.15 output per 1M tokens; Hy3 at $0.132 and $0.528. DeepSeek V4.1 Flash is 3.2x cheaper per token at list price.

Which has the larger context window?

DeepSeek V4.1 Flash accepts 1M tokens and Hy3 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.