modelbenchmark.io

Qwen3-Next 80B-A3B (Thinking)

Alibaba · qwen3-next-80b-a3b-thinking

Compare

Efficient Qwen thinking model for local reasoning, math, and coding agents

Specification

alibaba listing

Context
131K
Max output
33K
Released
2025-09
Knowledge cutoff
2025-04
Retires
2026-02-25
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · alibaba list price

Input
$0.50
Output
$6.00
Cache read
$0.075

Available from 16 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibabavendor$0.50$6.00——131K33K—
deepinfra$0.14$1.40——262K262K—
alibaba-cn$0.144$1.434——131K33K—
qiniu-ai$0.1449$1.4493——131K33K—
dashscope · dashscope$0.15$1.20——262K66K—
jalapeno$0.15$1.50——262K33K—
jiekou$0.15$1.50——66K66K—
merge-gateway$0.15$1.20——131K33K—
nano-gpt$0.15$0.65$0.075—256K33K—
nebius$0.15$1.20——128K128K—
novita$0.15$1.50——131K33K—
qwen_ai_platform · qwen-ai-platform$0.15$1.20——262K66K—
qwencloud · qwencloud$0.15$1.20——262K66K—
together_ai$0.15$1.50——262K262K2026-02-25
vercel$0.15$1.20——262K262K—
fireworks_ai$0.90$0.90——4K4K—

Price history

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

DateHostField$/M
2026-09-02nebiusInput$0.15
2026-09-06nebiusInput$0.15
2026-09-02openrouterInput$0.15
2026-09-06openrouterInput$0.15
2026-10-10openrouterInput$0.15
2026-09-02together_aiInput$0.15
2026-09-24together_aiInput$0.15
2026-09-02nebiusOutput$1.20
2026-09-06nebiusOutput$1.20
2026-09-02openrouterOutput$1.20
2026-09-06openrouterOutput$1.20
2026-10-10openrouterOutput$1.20
2026-09-02together_aiOutput$1.50
2026-09-24together_aiOutput$1.50

More from Alibaba

most-hosted first