Model

Llama-3.2-3B

Name: Llama-3.2-3B
Brand: meta

Small open Llama base model for lightweight text generation and self-hosting

2 providers · 2 listingsreleased Sep 25, 2024knowledge cutoff 2023-12open weights

$0.1

lowest input /M · Pioneer

$0.1

lowest output /M · Pioneer

131K

context window

131K

max output

Compare providers (sorted by listed input price)

2 providers list Llama-3.2-3B. The cheapest full-context option is Venice AI at $0.15/$0.6 per M. Pioneer lists lower but caps context at 131K.

			Cache read /M	Cache write /M		Capabilities	Status
Pioneer meta-llama/Llama-3.2-3B	$0.1	$0.1	$0.1	$0.1	131K	no reasoningno toolsno structuredno vision		Sep 25, 2024
Venice AI llama-3.2-3b	$0.15	$0.6	—	—	128K	no reasoningtoolsno structuredno vision		Jun 11, 2026

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.1unchanged
Best output /M: $0.1unchanged
Provider coverage: 2; 2 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![Llama-3.2-3B price](https://www.vaanalytics.in/badge/meta/llama-3.2-3b.svg)

https://www.vaanalytics.in/badge/meta/llama-3.2-3b.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Weights

Conditionalllama3.2Access request3.2B params

Commercial use allowed, but the lab attaches conditions — read them before shipping. Hugging Face requires you to accept terms, and the lab may approve access manually.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.