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

Phi-4-mini

microsoft· 2024-12-11· 128K ctx
open weights quant: unknown

spread (output)

2.3×

$0.300 – $0.680 · 3 providers

3 providers priced
ProviderInputOutputCache rdBlended
Nvidia
relay router
free/—free/——free/—
Azure
hyperscaler
$0.075$0.300—$0.095*
Azure Cognitive Services
unknown
$0.075$0.300—$0.095*
NanoGPT
relay router
$0.170$0.680$0.085$0.162

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