AiCostCompare

DeepSeek V4 Pro 0813 (batch)

by DeepSeek · deepseek/deepseek-v4-pro-0813:batch · #232 cheapest of 422 paid models

Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

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

Pricing

Input

$0.66

per 1M tokens

Output

$1.98

per 1M tokens

Blended (3:1)

$0.99

3 input : 1 output

Cache read

$0.022

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V4 Pro 0813 (batch) with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.99$0.0693
50%$0.751$0.0374−46%
90%$0.559$0.0119−83%

*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$0.000924$0.924
Document summary8,0001,000$0.00726$7.26
Codebase question (RAG)30,0002,000$0.0238$23.76
Long-context analysis150,0005,000$0.1089$108.90

Performance

Intelligence Index

36.3

AA composite quality

Coding Index

68.8

Math Index

Agentic Index

42.3

Output speed

median

Time to first token

median

Time to first answer

after reasoning tokens

Specs

Context window

1.05M

tokens

Max output

944K

tokens

Input modalities

text

Tokenizer

DeepSeek