TokenCosts AI.iov1.0
Back to Models Directory
DeepSeekdeepseek-v3

DeepSeek-V3 (deepseek-chat) API Pricing

Official PricingCall via OpenRouter

General-purpose MoE model (671B total, 37B active). Automatic server-side context caching offers ~74.1% savings on cached hits. No async batch endpoint, but offers off-peak nighttime discounts (00:30-08:30 UTC+8) of 50%.

Base Input Price$0.27/ 1M tokens
Base Output Price$1.10/ 1M tokens
Prompt Cache Read$0.070-74.07% 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$0.27$1.10SupportedConnect
OpenRouter$0.27$1.10SupportedConnect

Head-to-Head Comparisons for DeepSeek-V3 (deepseek-chat)

DeepSeek-V3 (deepseek-chat) vs OpenAI: GPT-6.1 Sol$0.27/M vs $2/M
DeepSeek-V3 (deepseek-chat) vs GPT-4o (Omni)$0.27/M vs $2.5/M
DeepSeek-V3 (deepseek-chat) vs Claude 3.5 Sonnet$0.27/M vs $3/M
DeepSeek-V3 (deepseek-chat) vs DeepSeek-R1 (deepseek-reasoner)$0.27/M vs $0.55/M