DeepSeek: DeepSeek V4.1 Flash
deepseek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
- Context window
- 1,048,576 tokens
- Input cost
- $0.04 / 1M
- Output cost
- $0.50 / 1M
- Latency (p50)
- —
