DeepSeek V4.1 Flash vs Mercury 3

Price, context window & benchmark comparison

DeepSeek V4.1 Flash

DeepSeek

$0.045 / $0.50

Input / Output · per 1M tokens

Mercury 3

Inception

$0.10 / $0.35

Input / Output · per 1M tokens

Compare different models

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

	DeepSeek V4.1 Flash	Mercury 3
Input price / 1M	$0.045	$0.10
Output price / 1M	$0.50	$0.35
Blended price (3:1)	$0.16	$0.16
Cached input / 1M	$0.006	$0.01
Context window	1M	1M
Max output	944K	131K
Intelligence index	—	—
Coding index	—	—
Providers	40	—
Best provider uptime (30m)	100.0%	—
Vision input	Yes	No
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-09-10	2026-10-16
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, DeepSeek V4.1 Flash or Mercury 3?

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

DeepSeek V4.1 Flash vs Mercury 3: which has a bigger context window?

DeepSeek V4.1 Flash: 1,048,576 tokens. Mercury 3: 1,000,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4.1 Flash ≈ $340.00, Mercury 3 ≈ $375.00.

More comparisons