Compare AI models

Specifications
Parameters
—0.5B/1.5B/3B/7B/14B/32B/72B
Context window
200k128k
API pricing
Cheapest input
—$0.288DeepInfra
Cheapest output
—$0.32DeepInfra
—$92.00DeepInfra · fp8
These models have no shared benchmark scores.
Overview
CompanyOpenAIQwen
Release dateMay 16 2025Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

codex-mini-latest and Qwen2.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5 shipped 239 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (codex-mini-latest) vs 128k (Qwen2.5). codex-mini-latest is closed, while Qwen2.5 is open weight.

Direct benchmark comparisons are unavailable — codex-mini-latest and Qwen2.5 don't publish scores on any of the same benchmarks.