AiCostCompare

DeepSeek V4 Flash 0731

by DeepSeek · deepseek/deepseek-v4-flash-0731 · #42 cheapest of 457 paid models

Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

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

Pricing

Input

$0.06

per 1M tokens

Output

$0.18

per 1M tokens

Blended (3:1)

$0.09

3 input : 1 output

Cache read

$0.015

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V4 Flash 0731 with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.09$0.0063—
50%$0.073$0.00405−36%
90%$0.06$0.00225−64%

*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$8.40e-5$0.084
Document summary8,0001,000$0.00066$0.66
Codebase question (RAG)30,0002,000$0.00216$2.16
Long-context analysis150,0005,000$0.0099$9.90

Performance

Intelligence Index

—

AA composite quality

Coding Index

69.1

Math Index

—

Agentic Index

41

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,229
UI components1,225
Data viz1,169
SVG1,169
3D1,188
Game dev1,197
Code categories1,217
ASCII art1,082

Specs

Context window

1.05M

tokens

Max output

384K

tokens

Input modalities

text

Tokenizer

DeepSeek