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

Qwen3.5 27B

alibaba· 2026-02-23· 262K ctx· apache-2.0
open weights quant: unknown

spread (output)

3.8×

$0.688 – $2.60 · 18 providers

18 providers priced
ProviderInputOutputCache rdBlended
EmpirioLabs AItiered
relay router
$0.086$0.688$0.086$0.141
OrcaRouter
relay router
$0.086$0.688—$0.141*
Merge Gateway
unknown
$0.086$0.688$0.017$0.097
Kilo Gateway
relay router
$0.195$1.56—$0.319*
OpenRouter
unknown
$0.195$1.56—$0.319*
SiliconFlow
relay router
$0.250$2.00—$0.409*
Ofox
relay router
$0.290$2.05$0.290$0.450
Ofox
relay router
$0.290$2.05$0.290$0.450
SiliconFlow (China)
relay router
$0.260$2.09—$0.427*
NanoGPT
relay router
$0.270$2.16$0.135$0.356
NanoGPT
relay router
$0.300$2.40$0.150$0.396
Hugging Face
relay router
$0.300$2.40—$0.491*
Jalapeno Cloud
relay router
$0.300$2.40—$0.491*
Mixlayer
relay router
$0.300$2.40—$0.491*
Alibaba
first party lab
$0.300$2.40—$0.491*
NovitaAI
relay router
$0.300$2.40—$0.491*
Requesty
relay router
$0.260$2.60—$0.473*
Deep Infra
open weights host
$0.260$2.60—$0.473*

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