Nemotron 3 Super 120B API pricing on Deep Infra
Every Deep Infra Nemotron 3 Super 120B rate we track, compared against 3 providers serving the same model.
Deep Infra currently has the cheapest Nemotron 3 Super 120B input price among the 3 providers we track.
Deep Infra Nemotron 3 Super 120B rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.085/1M | $0.400/1M |
About Nemotron 3 Super 120B
- Creator
- NVIDIA
- Context
- 262K
- Modalities
- text
Nemotron 3 Super 120B on other providers
About Deep Infra
Deep Infra is an AI inference cloud that provides serverless APIs for 100+ models and dedicated GPU rentals. Features OpenAI-compatible endpoints, custom model deployments, and infrastructure optimized for scale.
Frequently Asked Questions
How much does Nemotron 3 Super 120B cost on Deep Infra?
Deep Infra serves Nemotron 3 Super 120B from $0.085 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is Deep Infra the cheapest way to run Nemotron 3 Super 120B?
Of the 3 providers we track serving Nemotron 3 Super 120B, Deep Infra currently has the lowest input price. Rates change often, and throughput and latency differ between providers — check the comparison above before committing.
Does Deep Infra offer batch or cached pricing for Nemotron 3 Super 120B?
We track 1 Nemotron 3 Super 120B offering from Deep Infra. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.