Compare AI models

Specifications
Parameters
16B—
Context window
32k1M
API pricing
Input price
—$2.00
Output price
—$8.00
Cached input price
—$0.50
Cheapest input
—$2.00Azure
Cheapest output
—$8.00Azure
—$800OpenAI list price
Benchmarks
HumanEval
57.3%94.5%
MMLU
55.7%90.2%
Overview
CompanyDeepSeekOpenAI
Release dateMay 16 2024Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.1 leads DeepSeek V2 Lite on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Only GPT-4.1 has a verified first-party price for an available API: $2.00 per million input tokens and $8.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V2 Lite. DeepSeek V2 Lite shipped 333 days before GPT-4.1, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (DeepSeek V2 Lite) vs 1M (GPT-4.1). DeepSeek V2 Lite is open weight, while GPT-4.1 is closed.

On HumanEval, GPT-4.1 leads at 94.5% vs DeepSeek V2 Lite at 57.3%. On MMLU, GPT-4.1 leads at 90.2% vs DeepSeek V2 Lite at 55.7%.