DeepSeek V4.1 Flash vs DeepSeek V4 Flash
| Spec | DeepSeek V4.1 Flash | DeepSeek V4 Flash |
|---|---|---|
| Respan Index | 52.5 (#36) | 45.4 (#54) |
| Blended price per 1M | $0.089 | $0.113 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.051 / $0.203 | $0.09 / $0.18 |
| Max output | 384K | - |
| Input | text, vision | text |
| Released | 2026-09-10 | 2026-07-31 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | DeepSeek V4.1 Flash | DeepSeek V4 Flash |
|---|---|---|
| Coding | 43.7 DeepSeek V4.1 Flash | 29.7 DeepSeek V4 Flash |
| Agents | 58.3 DeepSeek V4.1 Flash | 58.0 DeepSeek V4 Flash |
| Reasoning | 55.5 DeepSeek V4.1 Flash | 46.1 DeepSeek V4 Flash |
| Knowledge & language | 44.5 DeepSeek V4.1 Flash | 35.5 DeepSeek V4 Flash |
| Human preference | 58.0 DeepSeek V4.1 Flash | 55.9 DeepSeek V4 Flash |
Benchmarks both report
DeepSeek V4.1 Flash leads on 16 of the 18 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Flash |
|---|---|---|
| LMArena Elo | 1475 | 1436 |
| LMArena WebDev (LMArena) | 1659 | 1582 |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 24.4% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 67.4% | 57.5% |
| GPQA Diamond | 90.9% | 91% |
| Mystery Game Puzzles (Epoch AI) | 43% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.3% | 94.4% |
| Terminal-Bench 4.0 (Vals AI) | 19.7% | 18.7% |
| Chess Puzzles (Epoch AI) | 48% | 32% |
| SimpleQA Verified | 42.9% | 33.6% |
| LiveBench Agentic Coding (LiveBench) | 77.3% | 46.8% |
| LiveBench Coding (LiveBench) | 80% | 75% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 79.3% |
| LiveBench Instruction Following (LiveBench) | 70% | 65.5% |
| LiveBench Language (LiveBench) | 81.2% | 79.2% |
| LiveBench Mathematics (LiveBench) | 93.3% | 86.8% |
| LiveBench Reasoning (LiveBench) | 86.7% | 86.6% |
| SimpleBench (SimpleBench) | 66.7% | 61.1% |
FAQ
Is DeepSeek V4.1 Flash better than DeepSeek V4 Flash?
DeepSeek V4.1 Flash scores 52.5 on the Respan Index (#36), ahead of DeepSeek V4 Flash at 45.4 (#54). DeepSeek V4.1 Flash leads on 16 of the 18 benchmarks both report.
Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Flash?
DeepSeek V4.1 Flash lists at $0.051 input and $0.203 output per 1M tokens; DeepSeek V4 Flash at $0.09 and $0.18. DeepSeek V4.1 Flash is 1.3x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsMuse Spark 1.3 vs DeepSeek V4 Flash
- vsGemini 3.8 Flash vs DeepSeek V4.1 Flash
- vsDeepSeek V4.1 Flash vs Qwen3.8-Max
- vsDeepSeek V4.1 Flash vs MiniMax M3.1 Flash
- vsDeepSeek V4.1 Flash vs Kimi K3
- vsDeepSeek V4 Flash vs Gemini 3.6 Flash
- vsDeepSeek V4 Flash vs GLM-5.3-Flash
- vsDeepSeek V4 Flash vs Muse Spark 1.2