Compare / DeepSeek-V4.1-Flash vs DeepSeek-V4.1-Flash-1017
DeepSeek-V4.1-Flash vs DeepSeek-V4.1-Flash-1017
Which is cheaper, which is more capable, and which does better at each kind of work, from 38 results on 2 sources that measured both models.
Of the 38 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 20 October 2026 (catalogue release 2026-10-20-96eb40c3ec63).
DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017? The short answer
DeepSeek-V4.1-Flash-1017 is newer, but DeepSeek-V4.1-Flash scores higher (Spring Prompt overall 53 against 44): stay on DeepSeek-V4.1-Flash unless the newer model does better on the results that match your work.
- Spring Prompt overall: DeepSeek-V4.1-Flash 53, DeepSeek-V4.1-Flash-1017 44 (out of 100; how the score works).
- DeepSeek-V4.1-Flash-1017 is cheaper to run: $0.002 against $0.006 per product listing on CatalogBench (3.9 times less).
- DeepSeek-V4.1-Flash-1017 scores higher on the Artificial Analysis Intelligence Index: 45.1 against 39.5.
- DeepSeek-V4.1-Flash writes faster: 369 tokens a second against 212.
- DeepSeek-V4.1-Flash-1017 is newer: released 17 Oct 2026, against 10 Sep 2026 for DeepSeek-V4.1-Flash.
- On our own benchmarks, on the results both models have: DeepSeek-V4.1-Flash does better for product listings.
- On third-party benchmarks, on the results both models have: DeepSeek-V4.1-Flash-1017 does better for agents and tool use and reasoning and knowledge.
Head to head
Every fact side by side
| DeepSeek-V4.1-Flash | DeepSeek-V4.1-Flash-1017 | |
|---|---|---|
| Price per million tokens | $0.30 in · $1.20 out | $0.30 in · $1.20 out |
| Blended (3 in : 1 out) | $0.52 | $0.52 |
| Cheapest host, blended | $0.11 (Decart, FP4) | – |
| Cost per product listing (CatalogBench) | $0.006 | $0.002 |
| Cached input, per million | $0.006 cached input | $0.006 cached input |
| Intelligence Index | 39.5 | 45.1 |
| Spring Prompt overall | 53 | 44 |
| Output speed, tokens a second | 369 | 212 |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Released | 10 Sep 2026 | 17 Oct 2026 (newer) |
| Weights | Open | Open |
| Developer based in | China | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
From our research
- DeepSeek-V4.1-Flash-1017 review: better at analysis, much worse at sticking to the product data 19 Oct 2026
- We Told 11 AI Models What Happened in 2026. Most of Them Thought We Were Making It Up. 12 Oct 2026
- Claude Haiku 5.5 Is Far Better Than Haiku 4.5 at a Tenth of the Price. GPT-6 Luna Still Beats It at Business Work. 8 Oct 2026
- Mistral Large 4 Is Fast, Cheap and Europe's Best Model. On Business Work, It Still Makes Things Up. 7 Oct 2026
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | DeepSeek-V4.1-Flash | DeepSeek-V4.1-Flash-1017 |
|---|---|---|
| CatalogBench measured by Spring Prompt · 3 results | ||
| Cost per productUS dollars, lower is better 7 · 4 of 24 measured | $0.0061 | $0.0015 |
| Reliably publish-ready% of products, higher is better 12 · 19 of 24 measured | 41.1% | 21.4% |
| Reliably publish-ready · sales brief% of products, higher is better 8 · 21 of 24 measured | 23.2% | 0.0% |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 32 · 16 of 249 measured | 39.5max reasoning | 45.1max reasoning |
| Humanity's Last Exam% of questions, higher is better 48 · 27 of 248 measured | 39.2%max reasoning | 43.3%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 20 · 16 of 118 measured | 26.8%max reasoning | 33.8%max reasoning |
Show all 38 results (32 more)
| Measure | DeepSeek-V4.1-Flash | DeepSeek-V4.1-Flash-1017 |
|---|---|---|
| CatalogBench measured by Spring Prompt · 28 results | ||
| Channel compliance% of products, higher is better 17 · 1 of 24 measured | 99.4% | 100.0% |
| Channel rules broken% of products, lower is better 23 · 19 of 24 measured | 3.0% | 1.2% |
| Channel rules broken · sales brief% of products, lower is better 21 · 22 of 24 measured | 1.8% | 2.4% |
| Claims to check% of products, lower is better 1 · 19 of 24 measured | 0.0% | 1.2% |
| Claims to check · sales brief% of products, lower is better 1 · 18 of 24 measured | 0.0% | 3.6% |
| Conflicts caught% of conflicts, higher is better 1 · 1 of 24 measured | 100.0% | 100.0% |
| Content quality% of checks, higher is better 13 · 20 of 24 measured | 96.7% | 95.3% |
| Content quality · sales brief% of checks, higher is better 16 · 19 of 24 measured | 96.2% | 94.8% |
| Decision accuracy% of decisions, higher is better 10 · 18 of 24 measured | 96.9% | 94.9% |
| Failed outputs% of products, lower is better 1 · 1 of 24 measured | 0.0% | 0.0% |
| Failed outputs · sales brief% of products, lower is better 20 · 1 of 24 measured | 0.6% | 0.0% |
| Field accuracy% of missing fields, higher is better 5 · 10 of 24 measured | 94.4% | 93.7% |
| Invented values% of filled values, lower is better 19 · 13 of 24 measured | 3.1% | 1.7% |
| Missing UK information% of products, lower is better 1 · 1 of 24 measured | 0.0% | 0.0% |
| Missing UK information · sales brief% of products, lower is better 1 · 1 of 24 measured | 0.0% | 0.0% |
| Not findable% of products, lower is better 5 · 5 of 24 measured | 3.6% | 3.6% |
| Not findable · sales brief% of products, lower is better 10 · 7 of 24 measured | 3.6% | 2.4% |
| Publish-ready listings% of products, higher is better 10 · 19 of 24 measured | 63.7% | 40.5% |
| Publish-ready listings · sales brief% of products, higher is better 8 · 21 of 24 measured | 47.0% | 8.3% |
| Time per productseconds, lower is better 15 · 3 of 24 measured | 17.6 | 6.70 |
| Unsupported claimsclaims per product, lower is better 11 · 21 of 24 measured | 0.54 | 1.70 |
| Unsupported claims% of products, lower is better 8 · 20 of 24 measured | 13.1% | 44.6% |
| Unsupported claims · sales briefclaims per product, lower is better 8 · 22 of 24 measured | 1.25 | 4.01 |
| Unsupported claims · sales brief% of products, lower is better 9 · 23 of 24 measured | 39.9% | 85.7% |
| Wrong attributes% of products, lower is better 18 · 13 of 24 measured | 20.2% | 17.9% |
| Wrong attributes · sales brief% of products, lower is better 16 · 21 of 24 measured | 20.2% | 22.0% |
| Wrong category or variant% of products, lower is better 15 · 2 of 24 measured | 3.0% | 0.6% |
| Wrong category or variant · sales brief% of products, lower is better 12 · 3 of 24 measured | 2.4% | 1.2% |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better 6 · 19 of 239 measured | 84.0%max reasoning | 82.7%max reasoning |
| Output speedtokens per second, higher is better 3 · 15 of 78 measured | 369no reasoning | 212max reasoning |
| SciCode% of problems, higher is better 42 · 24 of 119 measured | 51.9%max reasoning | 55.9%max reasoning |
| Time to first answer tokenseconds, lower is better 13 · 46 of 78 measured | 0.63no reasoning | 10.5max reasoning |
Compare them with other models
Quick answers
Is DeepSeek-V4.1-Flash better than DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash-1017 is newer, but DeepSeek-V4.1-Flash scores higher (Spring Prompt overall 53 against 44): stay on DeepSeek-V4.1-Flash unless the newer model does better on the results that match your work.
Which is cheaper, DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash-1017 is cheaper to run: $0.002 against $0.006 per product listing on CatalogBench (3.9 times less).
Which is faster, DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash writes about 369 tokens a second on its usual API, against 212 for DeepSeek-V4.1-Flash-1017 (Artificial Analysis).
Which is better for product listings, DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash ranks 10 of 24 models on sale for turning a sparse product feed and photos into listings that can go live, against 21 for DeepSeek-V4.1-Flash-1017.
Which is better for agents and tool use, DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash-1017 ranks 22 of 168 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 28 for DeepSeek-V4.1-Flash.
Which is better for reasoning and knowledge, DeepSeek-V4.1-Flash or DeepSeek-V4.1-Flash-1017?
DeepSeek-V4.1-Flash-1017 ranks 22 of 202 models on sale for hard questions across science, maths and general knowledge, against 40 for DeepSeek-V4.1-Flash.
Run DeepSeek-V4.1-Flash and DeepSeek-V4.1-Flash-1017 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.