DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is an AI model by DeepSeek that runs in anymize in the EU.
2 min readUpdated
What it is good for
Good for quick answers, coding and batch work at a very low price.
Hosting and operation
DeepSeek V4.1 Flash runs in data centres in the EU. It is operated by Melious.
If the operator is down, the model does not move to another jurisdiction.
Data processing
Data retention at the provider: none. Prompts and requests are not stored by the provider (zero data retention).
Data is not used for training.
With anonymization on, anymize replaces personal data with placeholders before the request reaches the model.
Technical data
| Item | Value |
|---|---|
| Context window | 1,000,000 tokens |
| Max. output | 384,000 tokens |
| Inputs | Text, Images |
| Capabilities | Tools, Reasoning |
| Class | Swift |
| Available since | 12 September 2026 |
Availability
The model is in the model catalog but not in the default selection. An admin adds it under Governance > Models, in a solo account you do it yourself.
Whether you may use it in a team is set by the “Model access” rule in the Governance Center.