DeepSeek V4 Flash 0731 vs GPT-4

Price, context window & benchmark comparison

DeepSeek V4 Flash 0731

DeepSeek

$0.03 / $0.32

Input / Output · per 1M tokens

GPT-4

OpenAI

$30.00 / $60.00

Input / Output · per 1M tokens

Compare different models

Verdict: DeepSeek V4 Flash 0731 is 365.9× cheaper than GPT-4 on a typical 3:1 input/output mix. DeepSeek V4 Flash 0731 has the larger context window (1.3M vs 8K).

	DeepSeek V4 Flash 0731	GPT-4
Input price / 1M	$0.03	$30.00
Output price / 1M	$0.32	$60.00
Blended price (3:1)	$0.10	$37.50
Cached input / 1M	$0.016	—
Context window	1.3M	8K
Max output	944K	4K
Intelligence index	34.3	—
Coding index	69.1	13.1
Providers	30	—
Best provider uptime (30m)	100.0%	—
Vision input	No	No
Reasoning	Yes	No
Tool calling	Yes	Yes
Released	2026-07-31	2023-05-28
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, DeepSeek V4 Flash 0731 or GPT-4?

DeepSeek V4 Flash 0731 is 365.9× cheaper than GPT-4 on a typical 3:1 input/output mix.

DeepSeek V4 Flash 0731 vs GPT-4: which has a bigger context window?

DeepSeek V4 Flash 0731: 1,310,720 tokens. GPT-4: 8,191 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4 Flash 0731 ≈ $220.00, GPT-4 ≈ $90,000.

DeepSeek V4 Flash 0731 vs GPT-4