DeepSeekdeepseek-v4-pro2026 Frontier

DeepSeek: DeepSeek V4 Pro 0423 API Pricing

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced re...

Base Input Price$0.96/ 1M tokens

Base Output Price$1.91/ 1M tokens

Prompt Cache Read$0.080-91.67% 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 Name	Input / 1M	Output / 1M	Prompt Caching	Access Endpoint
DeepSeek Direct	$0.96	$1.91	Supported	Connect
OpenRouter	$0.96	$1.91	Supported	Connect

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

DeepSeek: DeepSeek V4 Pro 0423 vs OpenAI: GPT-6.1 Sol$0.9553/M vs $2/M

DeepSeek: DeepSeek V4 Pro 0423 vs GPT-4o (Omni)$0.9553/M vs $2.5/M

DeepSeek: DeepSeek V4 Pro 0423 vs Claude 3.5 Sonnet$0.9553/M vs $3/M

DeepSeek: DeepSeek V4 Pro 0423 vs DeepSeek-V3 (deepseek-chat)$0.9553/M vs $0.27/M