open-source

Deepseek V3.2 vs Claude Sonnet 4 6

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

Specifications

Feature Deepseek V3.2 Claude Sonnet 4 6
Provider deepseek anthropic
Model ID deepseek/deepseek-v3.2 claude-sonnet-4-6
Input / 1M tokens $0.28 (91% cheaper) $3.00
Output / 1M tokens $0.40 (97% cheaper) $15.00
Cached input / 1M $0.30
Context window 164kk tokens 1000kk tokens
Max output 164kk tokens 64kk 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 Claude Sonnet 4 6 Winner
Small
1M in / 0.2M out
$0.36 $6.00 Deepseek V3.2 saves 94%
Medium
10M in / 2M out
$3.60 $60.00 Deepseek V3.2 saves 94%
Large
100M in / 20M out
$36.00 $600 Deepseek V3.2 saves 94%

Category winners

Cheapest input
Deepseek V3.2
$0.28/M · 91% less than the other
Cheapest output
Deepseek V3.2
$0.40/M · 97% less than the other
Larger context
Claude Sonnet 4 6
1000kk tokens · 510% larger window
More features
Claude Sonnet 4 6
4 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.30/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Claude Sonnet 4 6
Short interactions & high-throughput APIs
$0.40/M output — 97% cheaper on output at scale
Deepseek V3.2
Long-document processing & large codebases
1000k context window vs 164k — 510% larger context
Claude Sonnet 4 6
Agentic workflows & tool use
Supports 4 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Claude Sonnet 4 6

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.