← All models
D

DeepSeek R2

DeepSeek

DeepSeek's second-generation reasoning model — stronger than R1 across all benchmarks at similar cost

Input price$0.80 / 1M tokens
Output price$3.20 / 1M tokens
Context window128k tokens
Last updated2026-05-20

Quick calculator

tokens
tokens
req/day
Per request
$0.002400
Daily
$24.00
Monthly
$720.00
per month · 30-day estimate
Yearly
$8,760.00

Tips to reduce cost

  • Use prompt caching to reuse repeated system prompts
  • Trim whitespace and reduce verbose instructions
  • Use a smaller model for classification or routing tasks
  • Batch async requests to get 50% discount (OpenAI/Anthropic)
  • Cache identical requests at the application layer

Similar models from DeepSeek

Compared at your current token settings

About DeepSeek R2

DeepSeek R2 is a mid-range large language model from deepseek, priced at $0.8/1M input tokens and $3.2/1M output tokens. It is 69% cheaper than the market average and best suited for advanced reasoning at low cost. The 128k context window handles long documents, extended conversations, and large code files comfortably.

As a reasoning model, DeepSeek R2 generates internal thinking tokens before responding. These are billed at the output token rate and can add 2–5x to effective output cost. For tasks requiring deep reasoning — math, complex coding, multi-step analysis — this overhead is usually justified by fewer errors and retries.

DeepSeek R2 supports prompt caching at $0.2/1M — a 75% discount on repeated input tokens. For applications with a fixed system prompt or repeated document context (RAG, chatbots, agents), enabling caching is the single highest-leverage cost optimization available.

Frequently Asked Questions

How much does DeepSeek R2 cost per 1,000 tokens?
DeepSeek R2 costs $0.0008 per 1,000 input tokens and $0.0032 per 1,000 output tokens.
What is DeepSeek R2's context window?
DeepSeek R2 supports a context window of 128k tokens, which is suitable for long documents and multi-turn conversations.
How does DeepSeek R2 compare to GPT-4o on price?
DeepSeek R2 is 69% cheaper than the market average on input tokens. At $0.8/1M input vs $2.50/1M for GPT-4o, the cost difference becomes significant at scale — 10,000 requests/day with 1,000 input tokens each costs $240/month with DeepSeek R2 vs $750/month with GPT-4o.
Does DeepSeek R2 support prompt caching?
Yes. DeepSeek R2 supports prompt caching at $0.2/1M tokens — a 75% discount on repeated input. This is especially effective for RAG pipelines and chatbots with large system prompts that repeat across requests.

Compare DeepSeek R2 with other models

DeepSeek R2 vs Claude 3.5 HaikuDeepSeek R2 vs Claude Haiku 4.5DeepSeek R2 vs GPT-5 MiniDeepSeek R2 vs o4-miniDeepSeek R2 vs GPT-3.5 TurboDeepSeek R2 vs Gemini 3 Flash