AiCostCompare

DeepSeek V3 0324

by DeepSeek · deepseek/deepseek-chat-v3-0324 · #119 cheapest of 325 paid models

Prices updated Jul 22, 2026, 2:50 AM UTC · refreshed hourly

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

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

Pricing

Input

$0.27

per 1M tokens

Output

$1.12

per 1M tokens

Blended (3:1)

$0.483

3 input : 1 output

Cache read

$0.135

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V3 0324 with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.483$0.0287
50%$0.432$0.0219−24%
90%$0.391$0.0165−42%

*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$0.000471$0.471
Document summary8,0001,000$0.00328$3.28
Codebase question (RAG)30,0002,000$0.0103$10.34
Long-context analysis150,0005,000$0.0461$46.10

Performance

Intelligence Index

15.4

AA composite quality

Coding Index

21.2

Math Index

41

Agentic Index

1.5

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-Pro81.9%
GPQA Diamond65.5%
Humanity's Last Exam5.2%
LiveCodeBench40.5%
SciCode35.8%
MATH-50094.2%
AIME52.0%
AIME 202541.0%
IFBench41.0%
AA-LCR (Long Context Reasoning)41.0%
Terminal-Bench Hard15.2%
Terminal-Bench 2.113.9%
τ²-Bench (Telecom)47.1%
τ³-Bench Banking4.5%

Specs

Context window

164K

tokens

Max output

66K

tokens

Input modalities

text

Tokenizer

DeepSeek