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

Qwen Flash

alibaba· 2025-07-28· 1M ctx
API onlytool call quant: unknown

spread (output)

1.9×

$0.216 – $0.400 · 8 providers

8 providers priced
ProviderInputOutputCache rdBlended
Alibaba (China)
relay router
$0.022$0.216—$0.040*
Merge Gateway
unknown
$0.022$0.216$0.0044$0.028
Ofox
relay router
$0.022$0.220$0.0043$0.031
Ofox
relay router
$0.022$0.220$0.0043$0.031
LLMTR
relay router
$0.050$0.400—$0.082*
DevPass (LLM Gateway)
relay router
$0.050$0.400$0.010$0.062
LLM Gateway
relay router
$0.050$0.400$0.010$0.062
Alibaba
first party lab
$0.050$0.400—$0.082*

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