WIDEAREAINTELLIGENCE
← model directory

cloudflare

nvidia/nemotron-3-120b-a12b

cloudflare/nvidia/nemotron-3-120b-a12b

↓ runs free on your own hardware⚙ tool calling

NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.

specs & pricing
Type
text
Provider
cloudflare
Model ID
cloudflare/nvidia/nemotron-3-120b-a12b
Capabilities
tools
Context window
256K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.55 / 1M tokens
Output price
$1.65 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$2.20

$0.55 for a million input tokens plus $1.65 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

AI cost calculator →GPU power cost →

Run it on your own hardware

Estimated GPU memory for nvidia/nemotron-3-120b-a12b (120B parameters), for the weights alone — add room for the context cache.

Q4_K_M
~68.9 GBfits a 80 GB card
Q8_0
~119.2 GBmulti-GPU or large unified memory
FP16 / BF16
~224.3 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call nvidia/nemotron-3-120b-a12b through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardwareTry it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of nvidia/nemotron-3-120b-a12b?
nvidia/nemotron-3-120b-a12b accepts up to 256,000 tokens (256K) of context per request.
How much does nvidia/nemotron-3-120b-a12b cost per million tokens?
Through Wide Area Intelligence, nvidia/nemotron-3-120b-a12b costs $0.55 per 1M input tokens and $1.65 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $2.20.
Can I run nvidia/nemotron-3-120b-a12b on my own hardware?
Yes — nvidia/nemotron-3-120b-a12b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 68.9 GB of GPU memory, plus room for the context cache — it fits a single 80 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from cloudflare

← browse all models