原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
商品目录
探索公开商品信息,用清晰的条件缩小选择。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
DeepSeek-V4-Flash is the efficiency-oriented variant of the DeepSeek V4 series, released as a preview and open-sourced alongside the flagship V4-Pro. It is designed for developers who need the V4 generation's long-context and reasoning capability at a faster, more economical API tier. Compared with V4-Pro, V4-Flash uses smaller total parameters and active parameters, resulting in faster response times and lower API cost. It retains reasoning capability close to V4-Pro and matches V4-Pro on simple agent tasks, with a measurable gap appearing only on the most demanding agent workflows. World knowledge is slightly below V4-Pro but remains competitive within the open-source landscape.
DeepSeek-V4-Flash is the efficiency-oriented variant of the DeepSeek V4 series, released as a preview and open-sourced alongside the flagship V4-Pro. It is designed for developers who need the V4 generation's long-context and reasoning capability at a faster, more economical API tier. Compared with V4-Pro, V4-Flash uses smaller total parameters and active parameters, resulting in faster response times and lower API cost. It retains reasoning capability close to V4-Pro and matches V4-Pro on simple agent tasks, with a measurable gap appearing only on the most demanding agent workflows. World knowledge is slightly below V4-Pro but remains competitive within the open-source landscape.
DeepSeek V4 Flash 是低延迟、高吞吐模型,适合日常对话、基础推理、代码辅助和高并发场景,支持 1M Token 上下文。
DeepSeek V4 Flash 是低延迟、高吞吐模型,适合日常对话、基础推理、代码辅助和高并发场景,支持 1M Token 上下文。
原站按任务参数或阶梯规则计价,请在原站选择具体规格。
原站按任务参数或阶梯规则计价,请在原站选择具体规格。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
原站按任务参数或阶梯规则计价,请在原站选择具体规格。
DeepSeek V4.1 Flash model for reasoning and agentic coding
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
原站按任务参数或阶梯规则计价,请在原站选择具体规格。
原站按任务参数或阶梯规则计价,请在原站选择具体规格。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。
面向推理与智能体编程的 DeepSeek V4.1 Flash 模型
DeepSeek-V4-Flash,旧模型名,上游自 2026-09-10 起临时路由到 DeepSeek V4.1 Flash 并按 Flash 计费,1M 上下文 / 384K 最大输出。官方定价(高峰)输入 $0.30 / 输出 $1.20 / 缓存命中 $0.006 (每 1M tokens)。
DeepSeek-V4-Flash,旧模型名,上游自 2026-09-10 起临时路由到 DeepSeek V4.1 Flash 并按 Flash 计费,1M 上下文 / 384K 最大输出。官方定价(高峰)输入 $0.30 / 输出 $1.20 / 缓存命中 $0.006 (每 1M tokens)。
DeepSeek-V4-Flash,旧模型名,上游自 2026-09-10 起临时路由到 DeepSeek V4.1 Flash 并按 Flash 计费,1M 上下文 / 384K 最大输出。官方定价(高峰)输入 $0.30 / 输出 $1.20 / 缓存命中 $0.006 (每 1M tokens)。
DeepSeek V4.1 Flash model for reasoning and agentic coding
原站公开的站内额度标价;充值折扣、规格附加费及最终扣费以原站为准。