Compare AI models

Specifications
Parameters
16B3B
Context window
32k256k
API pricing
Input price
—$0.10
Output price
—$0.10
Cached input price
—$0.01
Cheapest input
—$0.10Mistral
Cheapest output
—$0.10Mistral
—$25.00Mistral list price
Benchmarks
MATH
27.9%83%
Overview
CompanyDeepSeekMistral
Release dateMay 16 2024Dec 2 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 3 3B-25-12 leads DeepSeek V2 Lite on 1 of the 1 benchmark they both report (MATH). Only Ministral 3 3B-25-12 has a verified first-party price for an available API: $0.10 per million input tokens and $0.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V2 Lite. DeepSeek V2 Lite shipped 565 days before Ministral 3 3B-25-12, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 Lite has 16B parameters, while Ministral 3 3B-25-12 has 3B. Context windows are 32k (DeepSeek V2 Lite) vs 256k (Ministral 3 3B-25-12).

On MATH, Ministral 3 3B-25-12 leads at 83% vs DeepSeek V2 Lite at 27.9%.