inferenstack — the market read on AI inference · last observation 2026-09-20. See the boards
Price spread

qwen/qwen3-vl-30b-a3b-instruct

qwen· 262K ctx· apache-2.0
API onlytool callstructured quant: unknown

spread (output)

1.9×

$0.520 – $1.00 · 9 providers

9 providers priced
ProviderInputOutputCache rdBlended
Kilo Gateway
relay router
$0.130$0.520—$0.165*
NEAR AI Cloud
relay router
$0.150$0.550—$0.186*
LLM Gateway
relay router
$0.150$0.600—$0.191*
DevPass (LLM Gateway)
relay router
$0.150$0.600—$0.191*
OpenRouter
unknown
$0.200$0.700—$0.245*
NovitaAI
relay router
$0.200$0.700—$0.245*
LLM Gateway
relay router
$0.200$0.700—$0.245*
SiliconFlowoutlier
relay router
$0.290$1.00—$0.355*
SiliconFlow (China)outlier
relay router
$0.290$1.00—$0.355*

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.