DeepSeek V4 Flash 0731 vs Mercury 2

Price, context window & benchmark comparison

DeepSeek V4 Flash 0731

DeepSeek

$0.03 / $0.32

Input / Output · per 1M tokens

Mercury 2

Inception

$0.25 / $0.75

Input / Output · per 1M tokens

Compare different models

Verdict: DeepSeek V4 Flash 0731 is 3.7× cheaper than Mercury 2 on a typical 3:1 input/output mix. DeepSeek V4 Flash 0731 has the larger context window (1.3M vs 128K).

	DeepSeek V4 Flash 0731	Mercury 2
Input price / 1M	$0.03	$0.25
Output price / 1M	$0.32	$0.75
Blended price (3:1)	$0.10	$0.38
Cached input / 1M	$0.016	$0.025
Context window	1.3M	128K
Max output	944K	50K
Intelligence index	34.3	—
Coding index	69.1	31.1
Providers	30	—
Best provider uptime (30m)	100.0%	—
Vision input	No	No
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-07-31	2026-03-04
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, DeepSeek V4 Flash 0731 or Mercury 2?

DeepSeek V4 Flash 0731 is 3.7× cheaper than Mercury 2 on a typical 3:1 input/output mix.

DeepSeek V4 Flash 0731 vs Mercury 2: which has a bigger context window?

DeepSeek V4 Flash 0731: 1,310,720 tokens. Mercury 2: 128,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4 Flash 0731 ≈ $220.00, Mercury 2 ≈ $875.00.

More comparisons