DeepSeek V4.1 Flash 1017 (Non-reasoning) vs DeepSeek V4 Pro 0813 (Max)
Which is better for the money: DeepSeek V4.1 Flash 1017 (Non-reasoning) by DeepSeek or DeepSeek V4 Pro 0813 (Max) by DeepSeek? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-01.
Depends on your budget
DeepSeek V4 Pro 0813 (Max) scores 4.6 points higher (23.1 vs 18.5) but costs 4.5× as much to run the benchmark ($1402 vs $310; premium vs mid-range cost classes). They are not alternatives at one budget: pick DeepSeek V4 Pro 0813 (Max) when you need intelligence above 18.5, and DeepSeek V4.1 Flash 1017 (Non-reasoning) when 18.5 is enough.
| Metric | DeepSeek V4.1 Flash 1017 (Non-reasoning) | DeepSeek V4 Pro 0813 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.5 | 23.1 | +24.9% DeepSeek V4 Pro 0813 … is 24.9% more intelligent |
| Total AA cost (lower is better) | $310.24 | $1,401.88 | +351.9% DeepSeek V4 Pro 0813 … is 4.5× more expensive |
| End-to-end time (lower is better) | 4.00s | 28.53s | +613.3% DeepSeek V4 Pro 0813 … is 613.3% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $1.32 / $3.96 | |
| Input modalities | Text, Image | Text |
DeepSeek V4 Pro 0813 (Max) vs DeepSeek V4.1 Flash 1017 (Non-reasoning): 24.9% more intelligence, 351.9% more cost to run the AA benchmark, and 613.3% slower end-to-end.
Against the frontier
- DeepSeek V4.1 Flash 1017 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Terra (High) scores 42.30 for $267.
- DeepSeek V4 Pro 0813 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.50 for $1124.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-1-flash-1017-non-reasoning/deepseek-v4-pro · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017-non-reasoning/deepseek-v4-pro?format=md · llms.txt · agent skill