Skip to main content
Amazon AWS logo

Llama 3.1 70B API pricing on Amazon AWS

Every Amazon AWS Llama 3.1 70B rate we track, compared against 3 providers serving the same model.

Input from /1M
$0.360
Output /1M
$0.360
Input price rank
#2 of 3
Last updated
November 21, 2026

The cheapest Llama 3.1 70B input price we currently track is $0.401/1M on Liquid Inference.

The cheapest Llama 3.1 70B output price is $0.401/1M on Liquid Inference.

Amazon AWS Llama 3.1 70B rates

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

Amazon AWS Llama 3.1 70B pricing by mode
ModeInputOutput
Batch$0.360/1M$0.360/1M
Standard$0.720/1M$0.720/1M

About Llama 3.1 70B

Creator
Meta
Context
128K
Modalities
text
Knowledge cutoff
Dec 2023
Tool calling
Yes
Open weights
Yes
Full Llama 3.1 70B details and every provider →Compare API pricing for every Llama model →

Llama 3.1 70B on other providers

About Amazon AWS

AWS provides a comprehensive suite of cloud computing services, including compute, storage, and GPU solutions for diverse workloads.

Frequently Asked Questions

How much does Llama 3.1 70B cost on Amazon AWS?

Amazon AWS serves Llama 3.1 70B from $0.360 per 1M input tokens, across 2 tracked pricing modes. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Amazon AWS the cheapest way to run Llama 3.1 70B?

Amazon AWS ranks #2 of 3 providers we track serving Llama 3.1 70B on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.401/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Amazon AWS offer batch or cached pricing for Llama 3.1 70B?

We track 2 Llama 3.1 70B offerings from Amazon AWS. 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.