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

qwen/qwen3-vl-32b-thinking

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

spread (output)

1.0×

$1.50 – $1.50 · 2 providers

2 providers priced
ProviderInputOutputCache rdBlended
SiliconFlow
relay router
$0.200$1.50—$0.318*
SiliconFlow (China)
relay router
$0.200$1.50—$0.318*

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