Compare AI models

Specifications
Context window
—1.05M
API pricing
Input price
$0.66$0.10
Output price
$1.98$0.50
Cached input price
$0.022$0.01
Cheapest input
$0.2442Baidu$0.05OpenAI
Cheapest output
$0.7326Baidu$0.25OpenAI
Benchmarks
BullshitBench v2
35%59%
ARC-AGI-2
61.3%59.3%
Overview
CompanyDeepSeekOpenAI
Release dateAug 13 2026Sep 22 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Pro-0813 and GPT-6 Luna are evenly matched across the 2 benchmarks they both report (BullshitBench v2, ARC-AGI-2). GPT-6 Luna is cheaper on both input and output: $0.10 vs $0.66 per million input tokens, and $0.50 vs $1.98 per million output tokens. Figures are base-tier rates. DeepSeek-V4-Pro-0813 shipped 40 days before GPT-6 Luna, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Pro-0813 is open weight, while GPT-6 Luna is closed.

On BullshitBench v2, GPT-6 Luna leads at 59% vs DeepSeek-V4-Pro-0813 at 35%. On ARC-AGI-2, DeepSeek-V4-Pro-0813 leads at 61.3% vs GPT-6 Luna at 59.3%.