DeepSeek V4.1 Flash 1017 replaces V4.1 Flash in LU Labs Cloud
DeepSeek's October refresh of V4.1 Flash is live in LU Labs Cloud. Old picks and API calls move over on their own, the catalog price is lower, and here is what DeepSeek says changed.
DeepSeek published V4.1 Flash 1017 on 17 October 2026. Since 18 October, 21:54 UTC, it is the model behind the DeepSeek V4.1 Flash entry in LU Labs Cloud. The picker now shows it as DeepSeek V4.1 Flash 1017.
You do not have to do anything. If you had picked V4.1 Flash in a chat, saved it as your default or call it over the API with deepseek-ai/DeepSeek-V4.1-Flash, your requests now go to 1017. The old id keeps working.
What stays the same
DeepSeek calls 1017 a minor update to V4.1 Flash. The checkpoint on Hugging Face is the same size, 510.3 GB, under the same MIT licence. In the cloud it keeps everything the old entry had:
- 1,048,576 tokens of context
- image input
- native tool calls, so Agent mode and the coding agent run on it as before
- reasoning on every turn, with the Think button locked on for the reason we gave in September
Before the switch we ran the new version next to the old one: a tool call, an image to describe, and the same reasoning prompts. Both behaved the same way, so none of the settings changed.
What DeepSeek says is better
The release note says 1017 scores higher on benchmarks, finishes tasks faster and writes shorter outputs than the version before it. The model card adds a table. These are DeepSeek's numbers, run by DeepSeek, and they compare 1017 with the V4.1 Flash it replaces:
| Benchmark | V4.1 Flash | V4.1 Flash 1017 |
|---|---|---|
| HLE without tools | 36.8 | 42.6 |
| Terminal-Bench 4.0 | 31.2 | 42.3 |
| DeepSWE v1.1 | 74.2 | 77.0 |
| ProgramBench | 20.3 | 29.1 |
| AutomationBench | 54.8 | 60.5 |
| Agents' Last Exam | 31.8 | 35.4 |
| Apex Bench v1.1 | 64.6 | 72.1 |
| Chartography, with tools | 78.9 | 83.0 |
| BabyVision, with tools | 89.6 | 92.5 |
| ZeroBench, with tools | 49.0 | 51.0 |
The largest gains are on the long agent tests, Terminal-Bench 4.0 and ProgramBench. The three image tests move by two to four points.
We have not measured output length ourselves yet. If DeepSeek's claim holds, the same task costs fewer output tokens on 1017 than it did on V4.1 Flash.
For API users: the model card now recommends temperature 1.0 and top_p 1.0.
What it costs
The catalog price went down with the switch. DeepSeek V4.1 Flash 1017 draws 20,000 credits per million input tokens and 60,000 per million output tokens. Our September comparison quoted 30,000 and 120,000 for V4.1 Flash.
DeepSeek V4 Flash 0731 is still the cheaper choice for bulk work. It draws 18,000 credits per million output tokens, so about a third of what 1017 does, but it cannot read images.
Every plan and every credit pack carries the whole chat catalog, so there is no tier to buy for this model. The pricing page has the plans and packs.
Using it
Open the Studio, pick DeepSeek V4.1 Flash 1017 in Chat and type. The desktop app pulls the cloud catalog from the server, so the new entry is there without an update.
From your own code, create a personal API key in account settings, point any OpenAI-compatible client at https://lu-labs.ai/api/inference/v1 and use the model id deepseek-ai/DeepSeek-V4.1-Flash-1017. More on the model and a ready curl example are on the DeepSeek V4.1 Flash online page.