DeepSeek V4 Flash 0731 vs MiniMax M2-her

Price, context window & benchmark comparison

DeepSeek

DeepSeek V4 Flash 0731

DeepSeek
$0.0434 / $0.30
Input / Output · per 1M tokens
VS
MiniMax

MiniMax M2-her

MiniMax
$0.30 / $1.20
Input / Output · per 1M tokens
Compare different models
DeepSeek
MiniMax
Verdict: DeepSeek V4 Flash 0731 is 4.9× cheaper than MiniMax M2-her on a typical 3:1 input/output mix. DeepSeek V4 Flash 0731 has the larger context window (1M vs 66K).
DeepSeek V4 Flash 0731MiniMax M2-her
Input price / 1M$0.0434$0.30
Output price / 1M$0.30$1.20
Blended price (3:1)$0.11$0.52
Cached input / 1M$0.035$0.03
Context window1M66K
Max output944K2K
Intelligence index——
Coding index69.1—
Providers27—
Best provider uptime (30m)100.0%—
Vision inputNoNo
ReasoningYesNo
Tool callingYesNo
Released2026-07-312026-01-23
Retirement—2026-11-05

Cost calculator

FAQ

Which is cheaper, DeepSeek V4 Flash 0731 or MiniMax M2-her?

DeepSeek V4 Flash 0731 is 4.9× cheaper than MiniMax M2-her on a typical 3:1 input/output mix.

DeepSeek V4 Flash 0731 vs MiniMax M2-her: which has a bigger context window?

DeepSeek V4 Flash 0731: 1,048,576 tokens. MiniMax M2-her: 65,536 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4 Flash 0731 ≈ $236.80, MiniMax M2-her ≈ $1,200.

More comparisons