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

qwen/qwen3-8b

qwen· 41K ctx· apache-2.0
open weights quant: unknown

spread (output)

12×

$0.060 – $0.700 · 9 providers

9 providers priced · 2 omitted (stale)
ProviderInputOutputCache rdBlended
SiliconFlow (China)
relay router
$0.060$0.060—$0.060*
SiliconFlow
relay router
$0.060$0.060—$0.060*
NovitaAIfp8
relay router
$0.035$0.138—$0.044*
Pioneer
relay router
$0.200$0.200$0.200$0.216
Alibaba (China)
relay router
$0.072$0.287—$0.092*
NanoGPTstale
relay router
$0.110$0.450$0.110$0.141
OpenRouter
unknown
$0.117$0.455—$0.148*
Kilo Gateway
relay router
$0.117$0.455—$0.148*
NanoGPTstale
relay router
$0.470$0.470$0.235$0.320
NanoGPT
relay router
$0.470$0.470$0.235$0.320
Alibaba
first party lab
$0.180$0.700—$0.227*

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