Compare / head-to-head
DeepSeek V4.1 FlashvsDeepSeek V4 Pro
DeepSeek V4.1 Flash leads 2 of 3 shared benchmarks. DeepSeek V4.1 Flash is 3.1x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
DeepSeek V4.1 Flash leads · 1 tied
Cheaper per token
DeepSeek V4.1 Flash
3.1x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100%
DeepSeek
DeepSeek V4.1 Flash
DeepSeek · released 2026-09-10
textvision
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Quality
Benchmark matrix
3 shared · 0 only DeepSeek V4.1 Flash · 8 only DeepSeek V4 Pro| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| GPQA Diamond | 90.9% ↗ | 90.9% ↗epoch | 0 | Tie |
| DeepSWE v1.1 | 74.2% ↗ | 62.7% ↗ | +11.5 pt | DeepSeek V4.1 Flash |
| Terminal-Bench 2.1 | 90.6% ↗ | 87.9% ↗ | +2.7 pt | DeepSeek V4.1 Flash |
| Only DeepSeek V4.1 Flash reports · 0 | ||||
| DeepSeek V4.1 Flash reports nothing DeepSeek V4 Pro does not. | ||||
| Only DeepSeek V4 Pro reports · 8 | ||||
| AIME 2026 | not reported | 96.7% ↗matharena ⚠ | — | — |
| LMArena Elo | not reported | 1450.6 ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 2.4% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 45.3% ↗epoch | — | — |
| Humanity's Last Exam (with tools) | not reported | 60% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 96.7% ↗epoch | — | — |
| SimpleQA Verified | not reported | 47% ↗epoch | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 77.6% ↗epoch | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V4.1 Flash minus DeepSeek V4 Pro in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | DeepSeek V4.1 Flash | DeepSeek V4 Pro | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 384K tokens | 384K tokens | Tie |
| Input price / 1M | $0.14 ↗ | $0.435 ↗ | DeepSeek V4.1 Flash |
| Output price / 1M | $0.28 ↗ | $0.87 ↗ | DeepSeek V4.1 Flash |
| Cached input / 1M | $0.003 ↗ | $0.004 ↗ | DeepSeek V4.1 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.42 | $1.31 | DeepSeek V4.1 Flash |
| Modalities | text · vision | text | DeepSeek V4.1 Flash |
| Released | 2026-09-10 | 2026-08-13 | — |
| Cited benchmark scores | 3 | 11 | — |
Reliability
DeepSeek status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V4.1 Flash vs …
Models sharing the most benchmarksMore matchups
DeepSeek V4 Pro vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4.1 Flash and DeepSeek V4 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.