modelbenchmark.io

Qwen3 30b A3b Instruct 2507

Alibaba · qwen3-30b-a3b-instruct

Compare

Tool-capable chat model for instruction following and agentic application workflows

Specification

most-agreed values

Context
262K
Max output
32K
Released
2026-02-04
Knowledge cutoff
2025-04
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.10
Output
$0.30
Cache read
$0.10
Cache write
$0.125

Available from 13 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
modelscopefreefree262K16K
openrouter
$0.0481
$0.09
$0.193
$0.30
262K32K
siliconflow$0.09$0.30262K262K
siliconflow-cn$0.09$0.30262K262K
cortecs$0.099$0.299262K262K
nebius$0.10$0.30$0.01$0.125262K
8K
262K
wandb$0.10$0.30$0.10262K262K
wandb · wandb$0.10$0.30262K
kilo$0.13$0.52128K32K
nano-gpt$0.20$0.50$0.10256K33K
clarifai$0.30$0.50262K262K
fireworks_ai$0.50$0.50262K262K
qiniu-ai128K32K

Price history

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

DateHostField$/M
2026-09-02nebiusInput$0.10
2026-09-06nebiusInput$0.10
2026-09-02openrouterInput$0.0481
2026-09-06openrouterInput$0.0481
2026-09-10openrouterInput$0.09
2026-09-13openrouterInput$0.0481
2026-09-02nebiusOutput$0.30
2026-09-06nebiusOutput$0.30
2026-09-02openrouterOutput$0.193
2026-09-06openrouterOutput$0.193
2026-09-10openrouterOutput$0.30
2026-09-13openrouterOutput$0.193

More from Alibaba

most-hosted first