DeepSeek V4: 1.6 Trillion Parameters, 1 Million Token Context
DeepSeek's V4-Pro debuts with 1.6 trillion parameters and a 1 million token context window as open weights, alongside a leaner 284B V4-Flash variant.
DeepSeek's V4-Pro debuts with 1.6 trillion parameters and a 1 million token context window as open weights, alongside a leaner 284B V4-Flash variant.