by Nex Agi

Nex-N2.5-Pro.

multimodal open weights datacenter 397B params 262K ctx
Cheapest input
$0.075/M
on OpenRouter
Cheapest output
$0.25/M
on OpenRouter
Smallest GPU
8× Nvidia Q RTX 8000
$2.10/hr
Run it yourself

Cheapest hardware per quantisation.

Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/h es la tarifa más baja disponible ahora. Una configuración multitarjeta usa una instancia real de ese tamaño cuando se alquila; si no, es la tarifa de una tarjeta por el número de tarjetas.

Quantisation Cheapest GPU config Total VRAM Live $/hr tokens/sec
FP16
FP16 — half precision (default)
1024 GB $12.41/hr
Cyfuture AI · bajo demanda
— Compare →
FP8
FP8 — 8-bit float (Hopper / Blackwell)
640 GB $5.73/hr
est. 8 × tarifa de una tarjeta
Nosana · bajo demanda
— Compare →
INT4
INT4 — 4-bit integer (~4× VRAM saving)
384 GB $2.10/hr
est. 8 × tarifa de una tarjeta
Vast.ai · bajo demanda
— Compare →
Just need an API?
Skip the GPU rental and call a hosted endpoint instead. See access providers on the Overview tab →