DeepSeek-V4.1-Flash-1017 vs DeepSeek V4 Pro
| Spec | DeepSeek-V4.1-Flash-1017 | DeepSeek V4 Pro |
|---|---|---|
| Respan Index | 59.3 (#23) | 49.2 (#45) |
| Blended price per 1M | $0.1 | $0.585 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.036 / $0.294 | $0.28 / $1.5 |
| Max output | - | 384K |
| Input | text, image | text |
| Released | 2026-10-17 | 2026-08-13 |
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-1017 | DeepSeek V4 Pro |
|---|---|---|
| Coding | 48.1 DeepSeek-V4.1-Flash-1017 | 29.8 DeepSeek V4 Pro |
| Agents | 76.3 DeepSeek-V4.1-Flash-1017 | 59.7 DeepSeek V4 Pro |
| Reasoning | 61.1 DeepSeek-V4.1-Flash-1017 | 52.8 DeepSeek V4 Pro |
| Knowledge & language | 42.7 DeepSeek-V4.1-Flash-1017 | 52.6 DeepSeek V4 Pro |
| Human preference | 57.9* DeepSeek-V4.1-Flash-1017 | 55.7 DeepSeek V4 Pro |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
DeepSeek-V4.1-Flash-1017 leads on 8 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek-V4.1-Flash-1017 | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents (Mercor) | 69.8% | 47.3% |
| Chess Puzzles (Epoch AI) | 46% | 46% |
| FrontierMath Tier 4 v2 (Epoch AI) | 46.3% | 26.8% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 71.2% | 64.6% |
| GPQA Diamond | 93.2% | 91.7% |
| Mystery Game Puzzles (Epoch AI) | 49% | 43% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.4% | 98.6% |
| SimpleQA Verified | 42.5% | 52.9% |
| Terminal-Bench 4.0 (Vals AI) | 31.8% | 14.1% |
| DeepSWE v1.1 | 77% | 62.7% |
FAQ
Is DeepSeek-V4.1-Flash-1017 better than DeepSeek V4 Pro?
DeepSeek-V4.1-Flash-1017 scores 59.3 on the Respan Index (#23), ahead of DeepSeek V4 Pro at 49.2 (#45). DeepSeek-V4.1-Flash-1017 leads on 8 of the 10 benchmarks both report.
Which is cheaper, DeepSeek-V4.1-Flash-1017 or DeepSeek V4 Pro?
DeepSeek-V4.1-Flash-1017 lists at $0.036 input and $0.294 output per 1M tokens; DeepSeek V4 Pro at $0.28 and $1.5. DeepSeek-V4.1-Flash-1017 is 5.8x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.