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

Qwen3.5 Flash

alibaba· 2026-02-23· 1M ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

4.0×

$0.260 – $1.03 · 10 providers

10 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
OpenRouter
unknown
$0.065$0.260—$0.083*
Merge Gateway
unknown
$0.029$0.287$0.0058$0.038
EmpirioLabs AI
relay router
$0.090$0.368$0.090$0.115
Ofox
relay router
$0.100$0.400$0.010$0.080
Ofox
relay router
$0.100$0.400$0.010$0.080
OrcaRouter
relay router
$0.100$0.400—$0.127*
Vercel AI Gateway
unknown
$0.100$0.400$0.010$0.080
ZenMux
relay router
$0.100$0.400—$0.127*
NanoGPTstale
relay router
$0.100$0.400$0.050$0.095
NanoGPT
relay router
$0.100$0.400$0.050$0.095
Alibaba (China)tieredoutlier
relay router
$0.172$1.03—$0.250*

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