DeepSeek V4.1 Flash is here
•just4o.chat
DeepSeek V4.1 Flash is in the model picker starting today. It is a quick, low-cost chat model, and it is available on every plan.
What it does
DeepSeek V4.1 Flash is an open-weight model. That means its maker has published the model itself, so independent companies can run it on their own servers.
Three things stand out:
- It reads images. Attach a photo, a screenshot or a scanned page and ask about it.
- It holds a lot. The context window is one million tokens. Long chats and large documents fit.
- It is cheap to use. Each send costs 2 base requests.
It does not search the web. If you need current information, pick a model with the web search icon in the picker.
Where it runs, and what happens to your chats
We know the question people ask about DeepSeek, so here is the plain answer.
On just4o.chat, DeepSeek V4.1 Flash runs on hosts in the United States and the European Union.
Requests are sent through the Vercel AI Gateway with zero data retention, and your chats are not used for training.
Your conversation history still lives in your just4o.chat account, the same as with every other model, so you can come back to it later.
What it costs
| Cost per send | 2 base requests |
| Image input | Yes |
| Web search | No |
| Context window | One million tokens |
| Privacy level | Zero data retention |
| Plans | Every plan |
Try it
Open chat and choose DeepSeek V4.1 Flash in the model picker. The full details are on the DeepSeek V4.1 Flash model page.
