Model
Inference & Serving
DeepSeek
1Strong 2open 3reasoning 4and 5chat 6models.
the six Ws · specification
W1
Who
Released by DeepSeek.
W2
What
Open-weight chat and reasoning models trained at low cost.
W3
Where
Weights run locally or via providers.
W4
When
When you need strong reasoning affordably.
W5
Why
Frontier-level reasoning from open weights.
W6
With
A model runtime or a hosted provider.
W7
Watch
MIT-licensed weights on Hugging Face; the hosted API sends data to DeepSeek.
alternatives
works with