Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
—$0.70
Output price
—$2.10
Cached input price
—$0.07
Cheapest input
$0.0507Baidu$0.70Mistral
Cheapest output
$0.2028Baidu$2.10Mistral
$20.28Baidu · fp8$245Mistral list price
Benchmarks
BullshitBench v2
57%80%
DeepSWE 1.1
74.2%61.7%
Terminal-Bench 4.0
31.2%41%
AutomationBench
54.8%59.9%
threejseval
16141008
Overview
CompanyDeepSeekMistral
Release dateSep 10 2026Oct 6 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 4 leads DeepSeek-V4.1-Flash on 3 of the 5 benchmarks they both report. Only Mistral Large 4 has a verified first-party price for an available API: $0.70 per million input tokens and $2.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V4.1-Flash. DeepSeek-V4.1-Flash shipped 26 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4.1-Flash) vs 1M (Mistral Large 4).

On BullshitBench v2, Mistral Large 4 leads at 80% vs DeepSeek-V4.1-Flash at 57%. On DeepSWE 1.1, DeepSeek-V4.1-Flash leads at 74.2% vs Mistral Large 4 at 61.7%. On Terminal-Bench 4.0, Mistral Large 4 leads at 41% vs DeepSeek-V4.1-Flash at 31.2%. On AutomationBench, Mistral Large 4 leads at 59.9% vs DeepSeek-V4.1-Flash at 54.8%. On threejseval, DeepSeek-V4.1-Flash leads at 1614 vs Mistral Large 4 at 1008.