LLMCost
deepseek

DeepSeek: DeepSeek V4 Flash 0423 API Pricing

DeepSeek: DeepSeek V4 Flash 0423 costs $0.049 per 1M input tokens and $0.098 per 1M output tokens (cache reads: $0.0098). Context window: 1.0M. Prices verified 2026-08-23 Β· source

Input / 1M tokens
$0.049
Output / 1M tokens
$0.098
Context window
1.0M
Max output
384K

What would DeepSeek: DeepSeek V4 Flash 0423 cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$0.78
Coding agent5,0008,000 / 2,000$2.93
RAG pipeline30,0004,000 / 500$7.33
Doc summarizer2,00020,000 / 1,000$2.15

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About DeepSeek: DeepSeek V4 Flash 0423

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Compare DeepSeek: DeepSeek V4 Flash 0423 with

Official resources