Qwen: Qwen3 30B A3B

Alibaba (Qwen)

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE)

Ultra-low cost
Text
Visit official site →Compare →

Specifications

VendorAlibaba (Qwen)
Familyqwen
Context131.1K · 98.3k words（≈ a thesis）
Max output131.1K · 98.3k words（≈ a thesis）
Released2026-06-19
Open sourceNo
Tool use—

Pricing across channels

per 1M tokens, USD

ChannelTypeInputOutput→
OpenRouter (auto)Aggregator$0.12$0.50visitAd
OpenRouter API (auto-fetched)· 2026-06-19

Related models

Similar tier, vendor or price range

Qwen: Qwen3 VL 30B A3B Instruct
Alibaba (Qwen)
Intel. —$0.13/$0.52
Qwen: Qwen3 VL 8B Instruct
Alibaba (Qwen)
Intel. —$0.080/$0.50
Qwen: Qwen3 VL 32B Instruct
Alibaba (Qwen)
Intel. —$0.10/$0.42
Qwen: Qwen3 30B A3B Thinking 2507
Alibaba (Qwen)
Intel. —$0.080/$0.40