Now served by DeepSeek-V4.1-Flash (API name deepseek-flash), DeepSeek's newest model and cheaper tier since September 2026: an open-weight 552B MoE with a 1M context. It replaced the retired V4-Flash.
$0.255 / 1M tokens Input$1.02 / 1M tokens Output
2 models
DeepSeek's largest model, an open-weight 1.6T-parameter MoE (49B active) with a 1M context and thinking on by default; the API has served an updated V4-Pro since August 2026. DeepSeek has announced V4.1-Pro as its successor.
$1.122 / 1M tokens Input$3.366 / 1M tokens Output
Page 1 of 1