Cloudflare AI

Nemotron 120B Cost Calculator

Estimate your exact monthly API cost for Nemotron 120B. Enter your token volume and see the math — OpenRouter vs Neureus side-by-side.

$0.45 Input /M (Neureus)

$1.35 Output /M (Neureus)

128K Context window

−10% vs OpenRouter

Published pricing

Input (OpenRouter) $0.50/M

Input (Neureus) $0.45/M

Output (OpenRouter) $1.50/M

Output (Neureus) $1.35/M

Monthly cost estimator

How much will Nemotron 120B cost?

Input tokens / month

Output tokens / month

Standard cost (OpenRouter)

—

N Neureus cost

—

You save — per month with Neureus

Cost breakdown

Type	Volume	Rate (OpenRouter)	Total (OpenRouter)	Rate (Neureus)	Total (Neureus)
Input	—	$0.50/M	—	$0.45/M	—
Output	—	$1.50/M	—	$1.35/M	—
Total			—		—

Model details

Context window

128K tokens

Maximum combined input + output size per request

Max output

4K tokens

Maximum tokens in a single response

Modalities

text, code

Input types supported by this model

Provider

Cloudflare AI

Access this model through Neureus or directly

NVIDIA Nemotron 120B MoE at the edge. Frontier-class model with deep reasoning and instruction adherence.

Full model documentation →

More Cloudflare AI models

Llama 3.3 70B

$0.26 input /M (Neureus)

128K context

Llama 4 Scout 17B

$0.24 input /M (Neureus)

128K context

DeepSeek R1 32B

$0.45 input /M (Neureus)

32K context

QwQ 32B

$0.59 input /M (Neureus)

32K context

Use Nemotron 120B for free.

Free tier includes 5M tokens — no credit card. Access Nemotron 120B and 34 other models through one API key, priced 10% below OpenRouter.

Start for free ← All model prices