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.
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.
| Mode | Input | Output |
|---|---|---|
| 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
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.