TokenCosts AI.iov1.0
Back to Models Directory
DeepSeekdeepseek-v4-flash-07312026 Frontier

DeepSeek: DeepSeek V4 Flash 0731 API Pricing

Official PricingCall via OpenRouter

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent wor...

Base Input Price$0.043/ 1M tokens
Base Output Price$0.30/ 1M tokens
Prompt Cache Read$0.035-19.35% 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$0.043$0.30SupportedConnect
OpenRouter$0.043$0.30SupportedConnect

Head-to-Head Comparisons for DeepSeek: DeepSeek V4 Flash 0731

DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-6.1 Sol$0.0434/M vs $2/M
DeepSeek: DeepSeek V4 Flash 0731 vs GPT-4o (Omni)$0.0434/M vs $2.5/M
DeepSeek: DeepSeek V4 Flash 0731 vs Claude 3.5 Sonnet$0.0434/M vs $3/M
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek-V3 (deepseek-chat)$0.0434/M vs $0.27/M