Skip to main content
Together AI logo

Llama 3.1 Nemotron 70B API pricing on Together AI

Every Together AI Llama 3.1 Nemotron 70B rate we track, compared against 2 providers serving the same model.

Input from /1M
$0.880
Output /1M
$0.880
Input price rank
#2 of 2
Last updated
November 21, 2026

The cheapest Llama 3.1 Nemotron 70B input price we currently track is $0.358/1M on Liquid Inference.

The cheapest Llama 3.1 Nemotron 70B output price is $0.409/1M on Liquid Inference.

Together AI Llama 3.1 Nemotron 70B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Together AI Llama 3.1 Nemotron 70B pricing by mode
ModeInputOutput
Standard$0.880/1M$0.880/1M

About Llama 3.1 Nemotron 70B

Creator
NVIDIA
Context
131K
Modalities
text
Open weights
Yes
Full Llama 3.1 Nemotron 70B details and every provider →Compare API pricing for every Nemotron model →

Llama 3.1 Nemotron 70B on other providers

About Together AI

Together AI is the AI Native Cloud platform engineered for developers building with open-source and frontier AI models. They provide serverless inference, fine-tuning, and GPU clusters with inference and training performance optimizations.

Frequently Asked Questions

How much does Llama 3.1 Nemotron 70B cost on Together AI?

Together AI serves Llama 3.1 Nemotron 70B from $0.880 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 Together AI the cheapest way to run Llama 3.1 Nemotron 70B?

Together AI ranks #2 of 2 providers we track serving Llama 3.1 Nemotron 70B on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.409/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Together AI offer batch or cached pricing for Llama 3.1 Nemotron 70B?

We track 1 Llama 3.1 Nemotron 70B offering from Together AI. 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.