Compare AI models

Specifications
Parameters
671B128B
Context window
128k256k
API pricing
Input price
—$1.50
Output price
—$7.50
Cached input price
—$0.15
Cheapest input
$0.256DeepInfra$1.50Mistral
Cheapest output
$0.712DeepInfra$7.50Mistral
$103StreamLake$675Mistral list price
Benchmarks
SWE-Bench Verified
42%77.6%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Apr 28 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3.5 leads DeepSeek V3 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only Mistral Medium 3.5 has a verified first-party price for an available API: $1.50 per million input tokens and $7.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 488 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mistral Medium 3.5 has 128B. Context windows are 128k (DeepSeek V3) vs 256k (Mistral Medium 3.5).

On SWE-Bench Verified, Mistral Medium 3.5 leads at 77.6% vs DeepSeek V3 at 42%.