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

modelsdev/phi4

modelsdev· 128K ctx
open weights quant: unknown

spread (output)

3.6×

$0.140 – $0.500 · 4 providers

4 providers priced
ProviderInputOutputCache rdBlended
Kilo Gateway
relay router
$0.070$0.140—$0.076*
OpenRouter
unknown
$0.070$0.140—$0.076*
Azure
hyperscaler
$0.125$0.500—$0.159*
Azure Cognitive Services
unknown
$0.125$0.500—$0.159*

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