Skip to main content
Together AI logo

Llama 3.2 3B API pricing on Together AI

Every Together AI Llama 3.2 3B rate we track, compared against 6 providers serving the same model.

Input from /1M
$0.060
Output /1M
$0.060
Input price rank
#5 of 6
Last updated
November 21, 2026

The cheapest Llama 3.2 3B input price we currently track is $0.020/1M on Liquid Inference.

The cheapest Llama 3.2 3B output price is $0.020/1M on Liquid Inference.

Together AI Llama 3.2 3B rates

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

Together AI Llama 3.2 3B pricing by mode
ModeInputOutput
Standard$0.060/1M$0.060/1M

About Llama 3.2 3B

Creator
Meta
Context
128K
Modalities
text
Tool calling
Yes
Open weights
Yes
Full Llama 3.2 3B details and every provider →Compare API pricing for every Llama model →

Llama 3.2 3B 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 3.2 3B cost on Together AI?

Together AI serves Llama 3.2 3B from $0.060 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 3.2 3B?

Together AI ranks #5 of 6 providers we track serving Llama 3.2 3B on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.020/1M 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 3.2 3B?

We track 1 Llama 3.2 3B 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.