DeepSeek-V4.1-Flash vs DeepSeek-V4-Flash-0731: Specs & Benchmark Comparison

DeepSeek-V4.1-Flash and DeepSeek-V4-Flash-0731 both come from DeepSeek, DeepSeek-V4-Flash-0731 was released in July 2026, and DeepSeek-V4.1-Flash followed 2 months later in September 2026. DeepSeek-V4.1-Flash is the larger model at roughly 552 billion parameters, against 304 billion for DeepSeek-V4-Flash-0731.

The two models share 5 published benchmarks. DeepSeek-V4.1-Flash leads on 5 of them. The widest gaps are on AutomationBench, where DeepSeek-V4.1-Flash scores 54.8% against 25.1%; CyberGym, where DeepSeek-V4.1-Flash scores 88.1% against 77.0%. Averaged across everything we track, DeepSeek-V4.1-Flash sits at 60.9% and DeepSeek-V4-Flash-0731 at 57.5%.

DeepSeek-V4-Flash-0731 is the cheaper API at $0.14 per million input tokens and $0.28 per million output tokens, roughly 2 times cheaper than DeepSeek-V4.1-Flash at $0.30 and $1.20. Both accept a context window of about 1M tokens. DeepSeek-V4.1-Flash accepts text and images as input, while DeepSeek-V4-Flash-0731 accepts text.

CharacteristicDeepSeek-V4.1-FlashDeepSeek-V4-Flash-0731
CompanyDeepSeekDeepSeek
Release DateSeptember 10, 2026July 31, 2026
Parameters552B304B
MultimodalYesNo
Context (input)1.0M1.0M
Context (output)393K393K
Input Price / 1M$0.30$0.14
Output Price / 1M$1.20$0.28
Average Score60.9%57.5%
Benchmarks
AutomationBench54.8%25.1%
CyberGym88.1%77.0%
NL2Repo64.0%54.2%
Terminal-Bench 2.190.6%83.0%
Agents' Last Exam31.8%25.2%

Visual Benchmark Comparison

DeepSeek-V4.1-Flash
DeepSeek-V4-Flash-0731
AutomationBench0.5 vs 0.3
0.5
0.3
CyberGym0.9 vs 0.8
0.9
0.8
NL2Repo0.6 vs 0.5
0.6
0.5
Terminal-Bench 2.10.9 vs 0.8
0.9
0.8
Agents' Last Exam0.3 vs 0.3
0.3
0.3

Verdict

DeepSeek-V4.1-Flash leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: DeepSeek-V4.1-Flash — 0.6, DeepSeek-V4-Flash-0731 — 0.6.

API Cost

DeepSeek-V4-Flash-0731 is 3.6x cheaper: input $0.14/1M vs $0.30/1M tokens.

Context Window

DeepSeek-V4.1-Flash supports a larger context: 1M vs 1M tokens.

Recency

DeepSeek-V4.1-Flash is newer: released 9/10/2026 vs 7/31/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — DeepSeek-V4.1-Flash or DeepSeek-V4-Flash-0731?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — DeepSeek-V4.1-Flash or DeepSeek-V4-Flash-0731?
DeepSeek-V4-Flash-0731 is cheaper for input: $0.14 per 1M tokens vs $0.30.
Which has a larger context window — DeepSeek-V4.1-Flash or DeepSeek-V4-Flash-0731?
DeepSeek-V4.1-Flash supports a larger context: 1,048,576 tokens vs 1,000,000.

The DeepSeek-V4.1-Flash and DeepSeek-V4-Flash-0731 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V4.1-Flash or DeepSeek-V4-Flash-0731 page. See also the complete list of AI model comparisons.