Skip to main content

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

SpecDeepSeek V4.1 FlashDeepSeek-V4.1-Flash-1017
Respan Index52.5 (#37)59.3 (#23)
Blended price per 1M$0.089$0.1
Context window1M1M
Input / output per 1M$0.051 / $0.203$0.036 / $0.294
Max output384K-
Inputtext, visiontext, image
Released2026-09-102026-10-17

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-V4.1-Flash-1017
Coding43.7 DeepSeek V4.1 Flash48.1 DeepSeek-V4.1-Flash-1017
Agents58.4 DeepSeek V4.1 Flash76.3 DeepSeek-V4.1-Flash-1017
Reasoning55.5 DeepSeek V4.1 Flash61.1 DeepSeek-V4.1-Flash-1017
Knowledge & language44.5 DeepSeek V4.1 Flash42.7 DeepSeek-V4.1-Flash-1017
Human preference57.5 DeepSeek V4.1 Flash57.9* DeepSeek-V4.1-Flash-1017

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

Benchmarks both report

DeepSeek-V4.1-Flash-1017 leads on 8 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V4.1 FlashDeepSeek-V4.1-Flash-1017
APEX-Agents (Mercor)39.5%69.8%
FrontierMath Tier 4 v2 (Epoch AI)26.8%46.3%
FrontierMath Tiers 1-3 v2 (Epoch AI)67.4%71.2%
GPQA Diamond90.9%93.2%
Mystery Game Puzzles (Epoch AI)43%49%
OTIS Mock AIME 2024-2025 (Epoch AI)98.3%99.4%
Terminal-Bench 4.0 (Vals AI)19.7%31.8%
Chess Puzzles (Epoch AI)48%46%
SimpleQA Verified42.9%42.5%
DeepSWE v1.174.2%77%

FAQ

Is DeepSeek V4.1 Flash better than DeepSeek-V4.1-Flash-1017?

DeepSeek-V4.1-Flash-1017 scores 59.3 on the Respan Index (#23), ahead of DeepSeek V4.1 Flash at 52.5 (#37). DeepSeek-V4.1-Flash-1017 leads on 8 of the 10 benchmarks both report.

Which is cheaper, DeepSeek V4.1 Flash or DeepSeek-V4.1-Flash-1017?

DeepSeek V4.1 Flash lists at $0.051 input and $0.203 output per 1M tokens; DeepSeek-V4.1-Flash-1017 at $0.036 and $0.294. DeepSeek V4.1 Flash is 1.1x 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.