open-source

Deepseek V3.2 vs Deepseek R1

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

Specifications

Feature Deepseek V3.2 Deepseek R1
Provider deepseek deepseek
Model ID deepseek/deepseek-v3.2 deepseek/deepseek-r1
Input / 1M tokens $0.28 (49% cheaper) $0.55
Output / 1M tokens $0.40 (82% cheaper) $2.19
Cached input / 1M
Context window 164kk tokens 66kk tokens
Max output 164kk tokens 8kk 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 V3.2 Deepseek R1 Winner
Small
1M in / 0.2M out
$0.36 $0.99 Deepseek V3.2 saves 64%
Medium
10M in / 2M out
$3.60 $9.88 Deepseek V3.2 saves 64%
Large
100M in / 20M out
$36.00 $98.80 Deepseek V3.2 saves 64%

Category winners

Cheapest input
Deepseek V3.2
$0.28/M · 49% less than the other
Cheapest output
Deepseek V3.2
$0.40/M · 82% less than the other
Larger context
Deepseek V3.2
164kk tokens · 150% larger window
More features
Deepseek V3.2
2 / 5 capabilities (tied)

Better for…

Short interactions & high-throughput APIs
$0.40/M output — 82% cheaper on output at scale
Deepseek V3.2
Long-document processing & large codebases
164k context window vs 66k — 150% larger context
Deepseek V3.2
Cost-sensitive production at scale
$36.00/month at 100M-token scale — 64% cheaper than the alternative
Deepseek V3.2

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.