DeepSeek V4.1 Flash vs Mercury 2.5

Price, context window & benchmark comparison

DeepSeek

DeepSeek V4.1 Flash

DeepSeek
$0.14 / $0.42
Input / Output · per 1M tokens
VS
Inception

Mercury 2.5

Inception
$0.04 / $0.15
Input / Output · per 1M tokens
Compare different models
DeepSeek
Inception
Verdict: Mercury 2.5 is 3.1× cheaper than DeepSeek V4.1 Flash on a typical 3:1 input/output mix. DeepSeek V4.1 Flash has the larger context window (1M vs 260K).
DeepSeek V4.1 FlashMercury 2.5
Input price / 1M$0.14$0.04
Output price / 1M$0.42$0.15
Blended price (3:1)$0.21$0.0675
Cached input / 1M$0.0042$0.004
Context window1M260K
Max output131K66K
Intelligence index39.5
Coding index
Providers26
Best provider uptime (30m)100.0%
Vision inputYesNo
ReasoningYesYes
Tool callingYesYes
Released2026-09-102026-09-08
Retirement

Cost calculator

FAQ

Which is cheaper, DeepSeek V4.1 Flash or Mercury 2.5?

Mercury 2.5 is 3.1× cheaper than DeepSeek V4.1 Flash on a typical 3:1 input/output mix.

DeepSeek V4.1 Flash vs Mercury 2.5: which has a bigger context window?

DeepSeek V4.1 Flash: 1,048,576 tokens. Mercury 2.5: 260,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4.1 Flash ≈ $490.00, Mercury 2.5 ≈ $155.00.

More comparisons