LLMCost
deepseek

DeepSeek: DeepSeek V3.1 API Pricing

DeepSeek: DeepSeek V3.1 costs $0.550 per 1M input tokens and $1.65 per 1M output tokens (cache reads: $0.550). Context window: 164K. Prices verified 2026-08-23 · source

Input / 1M tokens
$0.550
Output / 1M tokens
$1.65
Context window
164K
Max output
161K

What would DeepSeek: DeepSeek V3.1 cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$11.00
Coding agent5,0008,000 / 2,000$38.50
RAG pipeline30,0004,000 / 500$90.75
Doc summarizer2,00020,000 / 1,000$25.30

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Compare DeepSeek: DeepSeek V3.1 with