DeepSeek · Medium · Updated 2026-11

DeepSeek-R1 API Pricing & Cost Breakdown

Budget-friendly chain-of-thought reasoning, logic puzzles, and code verification.

Input / 1M Tokens
$0.55
Cached Input / 1M
$0.140
Output / 1M Tokens
$2.19
Context Window
64K

Workload Cost Scenarios (30-Day Billing)

Outputs visible <think> reasoning trace billed at output token rate.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $5.10 $4.18
Growing Startup (2,500 req/day) 2500 / 700 $218.10 $179.66
Production Scale (50,000 req/day) 3000 / 800 $5,103.00 $4,180.50

Compare DeepSeek-R1 Against Alternatives

Lower-Cost Alternative Models

Gemini 2.0 Flash ($0.40/1M out) Qwen 2.5 72B ($0.40/1M out) Grok 3 Mini ($0.50/1M out) GPT-4o mini ($0.60/1M out)

Frequently Asked Questions

What is DeepSeek-R1 API pricing per 1M tokens?

Standard input is $0.55/1M, cached input is $0.140/1M, and output is $2.19/1M.

What is the context window of DeepSeek-R1?

DeepSeek-R1 supports a 64K token context window with up to 8,192 max output tokens.

How much does prompt caching save on DeepSeek-R1?

Prompt caching reduces cached input token rates by 75% compared with uncached input.

What workloads is DeepSeek-R1 best suited for?

Budget-friendly chain-of-thought reasoning, logic puzzles, and code verification.