DeepSeek V4.1 Flash 1017 or DeepSeek V4.1 Flash?
Two builds of DeepSeek V4.1 Flash on the line. The 1017 build is DeepSeek's 17 October update and reads images; the September build is text only, writes longer replies and costs less.
| DeepSeek V4.1 Flash 1017 Outlaw | DeepSeek V4.1 Flash Outlaw | |
|---|---|---|
| Model id | deepseek-v4.1-flash-1017-outlaw | deepseek-v4.1-flash-outlaw |
| Intelligence Index (base model) | 39 | 39 |
| Context | 1,048,576 tokens | 1,048,576 tokens |
| Longest reply | 262,144 tokens | 393,216 tokens |
| Tool calling | Yes | Yes |
| Images | Yes | No |
| Reasoning | On by default, adjustable | On by default, adjustable |
| Input, per 1M tokens | $1.00 | $0.30 |
| Cached input, per 1M tokens | $0.25 | $0.20 |
| Output, per 1M tokens | $2.50 | $1.50 |
| A 25-turn agent session | $0.33 | $0.20 |
Intelligence Index is the Artificial Analysis Intelligence Index v4.3.2 for each base model; uncensored builds are not benchmarked separately. The agent session is about 750,000 input tokens re-read across 25 turns, 85% of them cache hits, and 25,000 tokens written. Prices are what Wild West API charges, checked 18 October 2026; the model pages always carry the current figures.
Use DeepSeek V4.1 Flash 1017 Outlaw when
- The job involves screenshots, diagrams or any other image. The 1017 build reads them; the September build is text only.
- You want DeepSeek's newer checkpoint. What the 1017 update changed has DeepSeek's own benchmark table against the September release.
Use DeepSeek V4.1 Flash Outlaw when
- The work is text. DeepSeek V4.1 Flash costs less for input, cached input and output.
- The reply is long. It writes up to 393,216 tokens in one reply against 262,144.
Trying both
Both answer on https://wildwestapi.com/v1 and the Anthropic-compatible endpoint with the same key, so the quickest comparison is your own prompt sent to each. The request is identical apart from the model id; the DeepSeek V4.1 Flash quickstart has it in curl, Python and JavaScript.
FAQ
What is the difference between DeepSeek V4.1 Flash Outlaw and DeepSeek V4.1 Flash 1017 Outlaw?
DeepSeek V4.1 Flash 1017 Outlaw is built on DeepSeek's 17 October 2026 update to V4.1 Flash. It reads images and writes up to 262,144 tokens in one reply; DeepSeek V4.1 Flash Outlaw is text only, writes up to 393,216 and costs less.
Do they score differently?
The Intelligence Index in the table is DeepSeek V4.1 Flash's, 39, for both builds; the 1017 update has no separate score there yet.
Can I switch between them?
Yes. Same endpoint, same key: change the model id from deepseek-v4.1-flash-1017-outlaw to deepseek-v4.1-flash-outlaw or back.