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

meta/llama-guard-4-12b

meta· 128K ctx
open weights quant: unknown

spread (output)

1.0×

$0.180 – $0.180 · 2 providers

2 providers priced
ProviderInputOutputCache rdBlended
Nvidia
relay router
free/—free/——free/—
Kilo Gateway
relay router
$0.180$0.180—$0.180*
OpenRouter
unknown
$0.180$0.180—$0.180*

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