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

nousresearch/hermes-4-405b

nousresearch· 128K ctx· llama3
open weightsstructured quant: unknown

spread (output)

2.5×

$1.20 – $3.00 · 5 providers

5 providers priced
ProviderInputOutputCache rdBlended
NanoGPT
relay router
$0.300$1.20$0.150$0.286
Cortecs
relay router
$0.996$2.99—$1.18*
Kilo Gateway
relay router
$1.00$3.00—$1.18*
Nebius Token Factory
relay router
$1.00$3.00$0.100$0.712
OpenRouter
unknown
$1.00$3.00—$1.18*

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