DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Pro 0813: a data-driven comparison

Side-by-side comparison

Criterion	DeepSeek V4.1 Flash 1017	DeepSeek V4 Pro 0813
Developer	DeepSeek	DeepSeek
Released	October 17, 2026	August 13, 2026
Capability index	90.6 / 100	72.2 / 100
Input price	$0.15	$0.66
Output price	$0.60	$1.98
Cost of a typical task	$0.004	$0.017
Context window	1,048,576 tokens	1,048,576 tokens
Maximum output	393,216 tokens	393,216 tokens
Reasoning mode	Yes	Yes
Tool calling	Yes	Yes
Accepted inputs	text, image	text
Open weights	Yes	Yes
Knowledge cutoff	May 2025	Not disclosed

Two models head to head

DeepSeek V4.1 Flash 1017 and DeepSeek V4 Pro 0813 are two open-weight models that you can install on your own servers, both built by DeepSeek. DeepSeek V4.1 Flash 1017 was released on October 17, 2026, DeepSeek V4 Pro 0813 on August 13, 2026.

All figures below come from public sources checked on October 22, 2026: models.dev and OpenRouter for prices and capabilities, Epoch AI for scores.

What the benchmarks say

On our capability index, DeepSeek V4.1 Flash 1017 scores 90.6 out of 100 and DeepSeek V4 Pro 0813 72.2. DeepSeek V4.1 Flash 1017 leads by 18.4 points.

On the 3 benchmarks reported for both, DeepSeek V4.1 Flash 1017 wins 3 times and DeepSeek V4 Pro 0813 0:

GPQA Diamond (PhD-level science questions): DeepSeek V4.1 Flash 1017 93.2%, DeepSeek V4 Pro 0813 91.7%
OTIS Mock AIME (competition mathematics problems): DeepSeek V4.1 Flash 1017 99.4%, DeepSeek V4 Pro 0813 98.6%
FrontierMath (very hard research-level mathematics): DeepSeek V4.1 Flash 1017 71.2%, DeepSeek V4 Pro 0813 64.6%

Budget

DeepSeek V4.1 Flash 1017 costs $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek V4 Pro 0813 costs $0.66 and $1.98.

For a typical agent task (read 20,000 tokens, write 2,000), expect $0.004 with DeepSeek V4.1 Flash 1017 versus $0.017 with DeepSeek V4 Pro 0813. DeepSeek V4.1 Flash 1017 is 4.1 times cheaper, a gap that adds up quickly over 1,000 tasks: $12.96 difference.

Run the numbers with your own volumes in the agent cost calculator.

Context and capabilities

Both models have the same context window: 1,048,576 tokens, roughly 1,573 pages.

Reasoning mode: DeepSeek V4.1 Flash 1017 yes, DeepSeek V4 Pro 0813 yes. Tool calling: DeepSeek V4.1 Flash 1017 yes, DeepSeek V4 Pro 0813 yes. Image input: DeepSeek V4.1 Flash 1017 yes, DeepSeek V4 Pro 0813 no.

Both publish their weights: you can host them yourself.

In short

Our reading of the data:

Choose DeepSeek V4.1 Flash 1017 for a higher capability index, a lower cost, a more recent release and image input.

This verdict relies on public figures; it does not replace a trial on your own tasks.

Frequently asked questions

DeepSeek V4.1 Flash 1017 or DeepSeek V4 Pro 0813: which is better?

On our index (Epoch AI data), DeepSeek V4.1 Flash 1017 scores 90.6 and DeepSeek V4 Pro 0813 72.2 out of 100. The best choice also depends on price and on your use case.

Which one is cheaper?

DeepSeek V4.1 Flash 1017. To read 20,000 tokens and write 2,000, expect $0.004 with DeepSeek V4.1 Flash 1017 and $0.017 with DeepSeek V4 Pro 0813 (prices as of October 22, 2026).

Which one has the larger context window?

Neither: both accept 1,048,576 tokens.

Can I run DeepSeek V4.1 Flash 1017 or DeepSeek V4 Pro 0813 on my own servers?

Yes, both publish their weights. Check each license before commercial use.

DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Pro 0813