TokenCosts AI.iov1.0
Back to Models Directory
DeepSeekdeepseek-v4-flash2026 Frontier

DeepSeek: DeepSeek V4 Flash 0423 API Pricing

Official PricingCall via OpenRouter

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...

Base Input Price$0.090/ 1M tokens
Base Output Price$0.18/ 1M tokens
Prompt Cache Read$0.018-80% discount
Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
DeepSeek Direct$0.090$0.18SupportedConnect
OpenRouter$0.090$0.18SupportedConnect

Head-to-Head Comparisons for DeepSeek: DeepSeek V4 Flash 0423

DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: GPT-6.1 Sol$0.09/M vs $2/M
DeepSeek: DeepSeek V4 Flash 0423 vs GPT-4o (Omni)$0.09/M vs $2.5/M
DeepSeek: DeepSeek V4 Flash 0423 vs Claude 3.5 Sonnet$0.09/M vs $3/M
DeepSeek: DeepSeek V4 Flash 0423 vs DeepSeek-V3 (deepseek-chat)$0.09/M vs $0.27/M