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

Nemotron 3.5 Lightning 30B A3B

nvidia· 2026-08-11· 1M ctx
open weightstool callreasoning quant: unknown

spread (output)

3.3×

$0.150 – $0.500 · 9 providers

9 providers priced
ProviderInputOutputCache rdBlended
OpenCode Zen
relay router
free/—free/—$0free/—
Merge Gateway
unknown
free/—free/——free/—
OpenRouter
unknown
free/—free/——free/—
Requesty
relay router
free/—free/——free/—
Kilo Gateway
relay router
free/—free/——free/—
Nvidia
relay router
free/—free/——free/—
RunInfrabf16
relay router
$0.050$0.150$0.010$0.034
Kilo Gateway
relay router
$0.040$0.180—$0.053*
Vercel AI Gateway
unknown
$0.050$0.200$0.010$0.038
NanoGPT
relay router
$0.050$0.200$0.010$0.038
NanoGPT
relay router
$0.080$0.200$0.040$0.065
OpenRouter
unknown
$0.070$0.200$0.040$0.063
Fireworks AI
relay router
$0.050$0.200$0.010$0.038
Nebius Token Factoryoutlier
relay router
$0.060$0.240$0.060$0.076
Pioneerbf16outlier
relay router
$0.500$0.500$0.500$0.541

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