Skip to main content
Liquid Inference logo

Llama 3.3 70B API pricing on Liquid Inference

Every Liquid Inference Llama 3.3 70B rate we track, compared against 14 providers serving the same model.

Input from /1M
$0.200
Output /1M
$0.520
Input price rank
#6 of 14
Last updated
November 21, 2026

The cheapest Llama 3.3 70B input price we currently track is $0.100/1M on Deep Infra.

The cheapest Llama 3.3 70B output price is $0.320/1M on Deep Infra.

Liquid Inference Llama 3.3 70B rates

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

Liquid Inference Llama 3.3 70B pricing by mode
ModeInputOutput
Standard$0.200/1M$0.520/1M

About Llama 3.3 70B

Creator
Meta
Context
128K
Modalities
text
Knowledge cutoff
Mar 2024
Tool calling
Yes
Open weights
Yes
Full Llama 3.3 70B details and every provider →Compare API pricing for every Llama model →

Llama 3.3 70B on other providers

About Liquid Inference

Liquid Inference is an AI exchange platform allowing model providers to compete to fulfill user prompts. Users set their requirements and receive offers from multiple providers.

Frequently Asked Questions

How much does Llama 3.3 70B cost on Liquid Inference?

Liquid Inference serves Llama 3.3 70B from $0.200 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 Liquid Inference the cheapest way to run Llama 3.3 70B?

Liquid Inference ranks #6 of 14 providers we track serving Llama 3.3 70B on input price. The cheapest input price right now is on Deep Infra. The lowest output price is $0.320/1M on Deep Infra. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Liquid Inference offer batch or cached pricing for Llama 3.3 70B?

We track 1 Llama 3.3 70B offering from Liquid Inference. 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.