deepseek-v4.1-flash

DeepSeek-V4.1-Flash is the lightweight flagship of DeepSeek's new architecture family, packing 552B total MoE parameters to deliver flagship-surpassing intelligence across key benchmarks, including out-performing DeepSeek-V4-Pro. It adopts a Causal Encoder-Decoder asymmetric design with 8B active parameters for input and 16B for output, and offers native multimodal visual understanding. KV Cache usage is cut to one-quarter of the previous generation's HBM and one-eighth of its SSD storage, drama

LiveDeepSeek3 个协议1M 上下文不支持流式取消
上下文
1M
输入 / 1M
$0.30
输出 / 1M
$1.20
Modalities
协议
3
  • chat.completions
  • messages
  • responses

可用性与性能

近 7 天
正在加载模型性能

能力

文本视觉长上下文缓存

计费明细

分时价格

按周循环 · Asia/Shanghai

命中时段后,该时段的完整价格会替代默认价格;不会从默认价格补齐缺失项。

00:0006:0012:0018:0024:00

默认价格

仅在每天未命中分时时段时生效
输入 Tokens
$0.3/1M
输出 Tokens
$1.20/1M
缓存命中
$0.03/1M
缓存输入
$0.03/1M

价格以 USD / 1M tokens 展示(除非另注单位)。Batch API 与缓存命中会享有额外折扣,最终以工作空间实时费率为准。