Llama 4 Maverick vs Ministral 3 14B 2512

Price, context window & benchmark comparison

M

Llama 4 Maverick

Meta Llama
$0.19 / $0.65
Input / Output · per 1M tokens
VS
M

Ministral 3 14B 2512

Mistral AI
$0.20 / $0.20
Input / Output · per 1M tokens
Compare different models
M
M
Verdict: Ministral 3 14B 2512 is 34% cheaper than Llama 4 Maverick on a typical 3:1 input/output mix. Llama 4 Maverick has the larger context window (1M vs 262K).
Llama 4 MaverickMinistral 3 14B 2512
Input price / 1M$0.19$0.20
Output price / 1M$0.65$0.20
Blended price (3:1)$0.30$0.20
Cached input / 1M$0.02
Context window1M262K
Max output16K210K
Intelligence index6
Coding index16.314.4
Providers53
Best provider uptime (30m)100.0%99.7%
Vision inputYesYes
ReasoningNoNo
Tool callingYesYes
Released2025-04-052025-12-02
Retirement

Cost calculator

FAQ

Which is cheaper, Llama 4 Maverick or Ministral 3 14B 2512?

Ministral 3 14B 2512 is 34% cheaper than Llama 4 Maverick on a typical 3:1 input/output mix.

Llama 4 Maverick vs Ministral 3 14B 2512: which has a bigger context window?

Llama 4 Maverick: 1,048,576 tokens. Ministral 3 14B 2512: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Llama 4 Maverick ≈ $701.25, Ministral 3 14B 2512 ≈ $500.00.

More comparisons