DeepSeek LLM API pricing

Every model DeepSeek serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models DeepSeek lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.

Models served

7

on this provider

Cheapest input

$0.14

per 1M tokens

Cheapest output

$0.28

per 1M tokens

Max context

1M

tokens

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Model ID
DeepSeek CoderDeepSeek128K$0.14$0.28deepseek/deepseek-coder
DeepSeek V3DeepSeek164K$0.27$1.10deepseek/deepseek-v3
DeepSeek ReasonerPointerDeepSeek131K$0.28$0.42deepseek-reasoner
DeepSeek V3PointerDeepSeek131K$0.28$0.42deepseek-chat
DeepSeek V3.2DeepSeek164K$0.28$0.40deepseek/deepseek-v3.2
DeepSeek FlashPointerDeepSeek1M$0.30$1.20deepseek-flash
DeepSeek V4 Flash 0423DeepSeek1M$0.30$1.20deepseek-v4-flash
DeepSeek V4 Flash Vision ExpDeepSeek1M$0.30$1.20deepseek-v4-flash-vision-exp
R1DeepSeek164K$0.55$2.19deepseek/deepseek-r1
DeepSeek V4 Pro 0423DeepSeek1M$1.32$3.96deepseek-v4-pro
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI