Compare AI models

Specifications
Parameters
671B—
Context window
128k400k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
These models have no shared benchmark scores.
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Sep 15 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 and GPT-5-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V3 shipped 263 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 400k (GPT-5-Codex). DeepSeek V3 is open weight, while GPT-5-Codex is closed.

Direct benchmark comparisons are unavailable — DeepSeek V3 and GPT-5-Codex don't publish scores on any of the same benchmarks.