All prices › DeepSeek › DeepSeek V3

DeepSeek V3 API pricing

As of October 16, 2026, DeepSeek V3 costs $0.27 per million input tokens and $1.10 per million output tokens on the DeepSeek API. Cached input is $0.07 per million.

It is the 3rd cheapest of 7 DeepSeek models tracked here, by blended price. The closest Budget-tier model from another provider is GPT-5.4 Nano (OpenAI) at $0.20 / $1.25; DeepSeek V3 is 3% more expensive. First listed in the LiteLLM price data on June 27, 2025.

Input / 1M tokens$0.27
Output / 1M tokens$1.10
Context window66K
Max output8K

Every published rate

RatePer 1M tokens
Input (standard)$0.27
Output (standard)$1.10
Cached input (read)$0.07

What it costs in practice

TaskTokensPer requestPer 1,000 requests
Chatbot reply1,000 in / 500 out$0.00082$0.82
Summarize a long document20,000 in / 1,000 out$0.0065$6.50
Coding agent step50,000 in / 2,000 out$0.02$15.70

Standard rates, no caching or batch discount. Compare your own numbers across all models →

Price history

DateModelChange
2025-06-27DeepSeek V3New model listed: $0.27 in / $1.1 out source

Dates are when each change first appeared in the LiteLLM price data, usually within days of the provider's announcement.

Details

ProviderDeepSeek
Price tierBudget
FeaturesPrompt caching, Tool use
API model namesdeepseek-v3
Official pricingapi-docs.deepseek.com

Models at a similar price

ModelInput / 1MOutput / 1M
Codestral$0.30$0.90
GPT-5.6 Luna$0.20$1.20
GPT-5.4 Nano$0.20$1.25
DeepSeek V4 Flash$0.30$1.20
Gemini 3.1 Flash Lite$0.25$1.50
GPT-5 Mini$0.25$2.00

Other DeepSeek models

ModelInput / 1MOutput / 1M
DeepSeek V4 Pro$1.32$3.96
DeepSeek R1$0.55$2.19
DeepSeek V4 Flash$0.30$1.20
DeepSeek V4 Flash Vision Exp$0.30$1.20
DeepSeek V3.2$0.28$0.40
DeepSeek Coder$0.14$0.28