DeepSeek-V4.1-Flash vs DeepSeek-V4-Pro-0813: Specs & Benchmark Comparison
DeepSeek-V4.1-Flash and DeepSeek-V4-Pro-0813 both come from DeepSeek, DeepSeek-V4-Pro-0813 was released in August 2026, and DeepSeek-V4.1-Flash followed a month later in September 2026. DeepSeek-V4-Pro-0813 is the larger model at roughly 1.6 trillion parameters, against 552 billion for DeepSeek-V4.1-Flash.
The two models share 8 published benchmarks. DeepSeek-V4.1-Flash leads on 6 of them, DeepSeek-V4-Pro-0813 on 2. The widest gaps are on Humanity's Last Exam, where DeepSeek-V4-Pro-0813 scores 60.0% against 36.8%; AutomationBench, where DeepSeek-V4.1-Flash scores 54.8% against 31.8%. Averaged across everything we track, DeepSeek-V4.1-Flash sits at 60.2% and DeepSeek-V4-Pro-0813 at 60.6%.
DeepSeek-V4.1-Flash is the cheaper API at $0.30 per million input tokens and $1.20 per million output tokens, roughly 4 times cheaper than DeepSeek-V4-Pro-0813 at $1.32 and $3.96. Both accept a context window of about 1M tokens. DeepSeek-V4.1-Flash accepts text and images as input, while DeepSeek-V4-Pro-0813 accepts text.
| Characteristic | DeepSeek-V4.1-Flash | DeepSeek-V4-Pro-0813 |
|---|---|---|
| Company | DeepSeek | DeepSeek |
| Release Date | September 10, 2026 | August 13, 2026 |
| Parameters | 552B | 1.6T |
| Multimodal | Yes | No |
| Context (input) | 1.0M | 1.0M |
| Context (output) | 393K | 393K |
| Input Price / 1M | $0.30 | $1.32 |
| Output Price / 1M | $1.20 | $3.96 |
| Average Score | 60.2% | 60.6% |
| Benchmarks | ||
| Humanity's Last Exam | 36.8% | 60.0% |
| AutomationBench | 54.8% | 31.8% |
| Agents' Last Exam | 31.8% | 25.7% |
| CyberGym | 88.1% | 83.0% |
| Humanity's Last Exam (with tools, text-only) | 63.9% | 60.0% |
| Humanity's Last Exam (no tools, text-only) | 39.1% | 42.7% |
| Terminal-Bench 2.1 | 90.6% | 88.0% |
| NL2Repo | 64.0% | 61.5% |
Visual Benchmark Comparison
Verdict
DeepSeek-V4.1-Flash leads in 2 out of 4 comparison categories.
Both models show comparable average scores: DeepSeek-V4.1-Flash — 0.6, DeepSeek-V4-Pro-0813 — 0.6.
DeepSeek-V4.1-Flash is 3.5x cheaper: input $0.30/1M vs $1.32/1M tokens.
Same context size: 1M tokens.
DeepSeek-V4.1-Flash is newer: released 9/10/2026 vs 8/13/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — DeepSeek-V4.1-Flash or DeepSeek-V4-Pro-0813?
Which model is cheaper — DeepSeek-V4.1-Flash or DeepSeek-V4-Pro-0813?
Which has a larger context window — DeepSeek-V4.1-Flash or DeepSeek-V4-Pro-0813?
The DeepSeek-V4.1-Flash and DeepSeek-V4-Pro-0813 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-Pro-0813 page. See also the complete list of AI model comparisons.