AiCostCompare

DeepSeek V3.2

by DeepSeek · deepseek/deepseek-v3.2 · #85 cheapest of 325 paid models

Prices updated Jul 22, 2026, 2:26 AM UTC · refreshed hourly

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.269

per 1M tokens

Output

$0.40

per 1M tokens

Blended (3:1)

$0.302

3 input : 1 output

Cache read

$0.134

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V3.2 with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.302$0.0278
50%$0.251$0.0211−24%
90%$0.211$0.0157−43%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000254$0.2545
Document summary8,0001,000$0.002552$2.55
Codebase question (RAG)30,0002,000$0.00887$8.87
Long-context analysis150,0005,000$0.0423$42.35

Performance

Intelligence Index

24.7

AA composite quality

Coding Index

44.2

Math Index

59

Agentic Index

18.3

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro83.7%
GPQA Diamond75.1%
Humanity's Last Exam10.5%
LiveCodeBench59.3%
SciCode38.7%
AIME 202559.0%
IFBench49.0%
AA-LCR (Long Context Reasoning)39.0%
Terminal-Bench Hard32.6%
τ²-Bench (Telecom)78.9%

Design Arena Elo

CategoryElo
Website1,201
UI components1,190
Data viz1,196
SVG1,079
3D1,192
Game dev1,191
Code categories1,197
ASCII art1,124

Specs

Context window

164K

tokens

Max output

66K

tokens

Input modalities

text

Tokenizer

DeepSeek