modelbenchmark.io

Qwen: Qwen3 14B

Alibaba · qwen3-14b-04-28

Compare

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Specification

most-agreed values

Context
41K
Max output
16K
Released
—
Knowledge cutoff
2025-03-31
Retires
—
Open weights
—
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.12
Output
$0.24

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openrouter$0.12$0.24——41K16K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.12
2026-09-03openrouterInput$0.2275
2026-09-04openrouterInput$0.12
2026-09-08openrouterInput$0.2275
2026-09-14openrouterInput$0.12
2026-10-10openrouterInput$0.10
2026-10-11openrouterInput$0.12
2026-09-02openrouterOutput$0.24
2026-09-03openrouterOutput$0.91
2026-09-04openrouterOutput$0.24
2026-09-08openrouterOutput$0.91
2026-09-14openrouterOutput$0.24
2026-10-10openrouterOutput$0.22
2026-10-11openrouterOutput$0.24

Other listings of this model

this page is one of them

The corpus files Qwen: Qwen3 14B under several keys. This page is the qwen3-14b-04-28 listing. The full record — every host, every price and every benchmark score — is on the main Qwen: Qwen3 14B page.

More from Alibaba

most-hosted first