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

Qwen3.5 122B-A10B

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

spread (output)

4.3×

$0.917 – $3.97 · 20 providers

20 providers priced
ProviderInputOutputCache rdBlended
Nvidia
relay router
free/—free/——free/—
Merge Gateway
unknown
$0.115$0.917$0.023$0.129
OrcaRouter
relay router
$0.115$0.917—$0.188*
EmpirioLabs AItiered
relay router
$0.115$0.917$0.115$0.188
SiliconFlow
relay router
$0.260$2.08—$0.426*
Kilo Gateway
relay router
$0.260$2.08—$0.426*
OpenRouter
unknown
$0.260$2.08—$0.426*
Neon
relay router
$0.220$2.20—$0.400*
Ofox
relay router
$0.290$2.29$0.290$0.472
Ofox
relay router
$0.290$2.29$0.290$0.472
SiliconFlow (China)
relay router
$0.290$2.32—$0.475*
Deep Infra
open weights host
$0.290$2.40—$0.482*
Jalapeno Cloud
relay router
$0.400$3.20—$0.655*
Hugging Face
relay router
$0.400$3.20—$0.655*
Mixlayer
relay router
$0.400$3.20—$0.655*
Alibaba
first party lab
$0.400$3.20—$0.655*
NovitaAI
relay router
$0.400$3.20—$0.655*
Cortecs
relay router
$0.495$3.46$0.124$0.529
NanoGPT
relay router
$0.437$3.50$0.104$0.503
TensorX
relay router
$0.500$3.50$0.125$0.586
Infomaniakfp8
relay router
$0.500$3.97—$0.816*

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