GPT-5.2-Codex vs Ministral 3 14B 2512

Price, context window & benchmark comparison

O

GPT-5.2-Codex

OpenAI
$1.75 / $14.00
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
O
M
Verdict: Ministral 3 14B 2512 is 24.1× cheaper than GPT-5.2-Codex on a typical 3:1 input/output mix. GPT-5.2-Codex has the larger context window (400K vs 262K).
GPT-5.2-CodexMinistral 3 14B 2512
Input price / 1M$1.75$0.20
Output price / 1M$14.00$0.20
Blended price (3:1)$4.81$0.20
Cached input / 1M$0.17$0.02
Context window400K262K
Max output128K210K
Intelligence index6
Coding index14.4
Providers3
Best provider uptime (30m)99.7%
Vision inputYesYes
ReasoningYesNo
Tool callingYesYes
Released2026-01-142025-12-02
Retirement

Cost calculator

FAQ

Which is cheaper, GPT-5.2-Codex or Ministral 3 14B 2512?

Ministral 3 14B 2512 is 24.1× cheaper than GPT-5.2-Codex on a typical 3:1 input/output mix.

GPT-5.2-Codex vs Ministral 3 14B 2512: which has a bigger context window?

GPT-5.2-Codex: 400,000 tokens. Ministral 3 14B 2512: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: GPT-5.2-Codex ≈ $10,500, Ministral 3 14B 2512 ≈ $500.00.

More comparisons