Model
DeepSeek V4 Pro 0423
The professional-tier model in the DeepSeek V4 series, supporting context caching. API usage is billed across three token categories: input, cached input and output.
Timeline (last 90 days)
Oct 19
DeepSeek V4 Pro 0423's channel input price is 40% lower than the official input price, and its output price is 51% lower.
Unverified50%