reasoning

Deepseek R1 vs Deepseek Reasoner

Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.

Specifications

Feature Deepseek R1 Deepseek Reasoner
Provider deepseek deepseek
Model ID deepseek/deepseek-r1 deepseek/deepseek-reasoner
Input / 1M tokens $0.55 $0.28 (49% cheaper)
Output / 1M tokens $2.19 $0.42 (81% cheaper)
Cached input / 1M $0.03
Context window 66kk tokens 131kk tokens
Max output 8kk tokens 66kk tokens
Vision
Function calling
Prompt caching
Web search
JSON schema

Monthly cost comparison

No cache discount applied — pure token costs at three usage scales.

Scale Deepseek R1 Deepseek Reasoner Winner
Small
1M in / 0.2M out
$0.99 $0.36 Deepseek Reasoner saves 63%
Medium
10M in / 2M out
$9.88 $3.64 Deepseek Reasoner saves 63%
Large
100M in / 20M out
$98.80 $36.40 Deepseek Reasoner saves 63%

Category winners

Cheapest input
Deepseek Reasoner
$0.28/M · 49% less than the other
Cheapest output
Deepseek Reasoner
$0.42/M · 81% less than the other
Larger context
Deepseek Reasoner
131kk tokens · 100% larger window
More features
Deepseek R1
2 / 5 capabilities (tied)

Better for…

High-volume RAG & repeated context
$0.03/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Deepseek Reasoner
Short interactions & high-throughput APIs
$0.42/M output — 81% cheaper on output at scale
Deepseek Reasoner
Long-document processing & large codebases
131k context window vs 66k — 100% larger context
Deepseek Reasoner
Cost-sensitive production at scale
$36.40/month at 100M-token scale — 63% cheaper than the alternative
Deepseek Reasoner

Deep-dive on each model

Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.