← All models
D

DeepSeek R1

DeepSeek

Open-source reasoning model matching o1-level performance at a fraction of the cost. Ideal for math, coding, logic.

Input price$0.55 / 1M tokens
Output price$2.19 / 1M tokens
Context window64k tokens
Last updated2026-04-21

Quick calculator

tokens
tokens
req/day
Per request
$0.001645
Daily
$16.45
Monthly
$493.50
per month · 30-day estimate
Yearly
$6,004.25

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 R1

DeepSeek R1 is a mid-range large language model from deepseek, priced at $0.55/1M input tokens and $2.19/1M output tokens. It is 79% cheaper than the market average and best suited for math & logic reasoning. The 64k context window covers most standard production workloads.

As a reasoning model, DeepSeek R1 generates internal thinking tokens before responding. These are billed at the output token rate and can add 2–4x 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 R1 supports prompt caching at $0.14/1M — 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 R1 cost per 1,000 tokens?
DeepSeek R1 costs $0.0006 per 1,000 input tokens and $0.0022 per 1,000 output tokens.
What is DeepSeek R1's context window?
DeepSeek R1 supports a context window of 64k tokens, which is suitable for standard use cases and moderate-length conversations.
How does DeepSeek R1 compare to GPT-4o on price?
DeepSeek R1 is 79% cheaper than the market average on input tokens. At $0.55/1M 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 $165/month with DeepSeek R1 vs $750/month with GPT-4o.
Does DeepSeek R1 support prompt caching?
Yes. DeepSeek R1 supports prompt caching at $0.14/1M 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 R1 with other models

DeepSeek R1 vs GPT-5 MiniDeepSeek R1 vs GPT-3.5 TurboDeepSeek R1 vs Gemini 3 FlashDeepSeek R1 vs Mistral Large 3DeepSeek R1 vs Llama 4 MaverickDeepSeek R1 vs GPT-4.1 Mini