Compare AI models

Specifications
Parameters
671B119B
Context window
128k256k
API pricing
Input price
—$0.15
Output price
—$0.60
Cached input price
—$0.015
Cheapest input
$0.256DeepInfra$0.15Mistral
Cheapest output
$0.712DeepInfra$0.60Mistral
$103StreamLake$60.00Mistral list price
Benchmarks
LiveCodeBench
40.5%63.6%
GPQA Diamond
59.1%71.2%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 4 leads DeepSeek V3 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Only Mistral Small 4 has a verified first-party price for an available API: $0.15 per million input tokens and $0.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 445 days before Mistral Small 4, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mistral Small 4 has 119B. Context windows are 128k (DeepSeek V3) vs 256k (Mistral Small 4).

On LiveCodeBench, Mistral Small 4 leads at 63.6% vs DeepSeek V3 at 40.5%. On GPQA Diamond, Mistral Small 4 leads at 71.2% vs DeepSeek V3 at 59.1%.