DeepSeek: DeepSeek V4 Flash
deepseek/deepseek-v4-flashIn preparation
Open text and coding model with a long context.
This model is part of the planned selection. The connection in the EU and the HanseRouter price are not settled yet. It cannot be used through the API yet.
- Context
- 256k
- Input
- Text only
- Input per 1M tokens
- Price to follow
- Output per 1M tokens
- Price to follow
Planned providers in the EU
The provider documents this model. The connection to HanseRouter is still pending. Context and features may differ between providers.
| Provider | Location | Context | Source |
|---|---|---|---|
| Scalewayplanned | France | 256k | Documentation |
Research as of 6 October 2026.
How to call the model
The example works as soon as the model is enabled.
curl https://api.hanserouter.eu/v1/chat/completions \
-H "Authorization: Bearer $HANSEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [{"role": "user", "content": "Summarise this text in two sentences."}]
}'