Model
DeepSeek-V4-Pro
DeepSeek's flagship open-weight MoE model (1.6T total / 49B active) for maximum reasoning, coding, and agentic performance, with a 1M-token context under an MIT license.
Model metadata
Modalities: text
Model
DeepSeek's flagship open-weight MoE model (1.6T total / 49B active) for maximum reasoning, coding, and agentic performance, with a 1M-token context under an MIT license.