Meta
EfficientPriced via OpenRouter

Llama 3.2 3B Instruct

text->text

Edge-targeted Llama 3.2, designed for on-device assistants on phones and laptops.

Llama 3.2 3B Instruct is a efficient AI model from Meta. It costs $0.0509 per million input tokens and $0.3350 per million output tokens (blended $0.1361/M), with a 131,072-token context window.

Profile inherited from upstream Llama 3.2 3B ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0509/M
per million input tokens
OUTPUT
$0.3350/M
per million output tokens
BLENDED 70/30
$0.1361/M

+1.6%over 91 days · hover to read

Llama 3.2 3B Instruct — blended price

Reconstructed from 91 days of recorded rate-card changes. Prices hold flat between changes because that is what a posted price does — no value here is interpolated.

CONTEXT
131,072
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Runs on-device
  • Open weights
  • 128K context
Typical use cases
  • Mobile/edge assistants
  • On-device summarisation

Benchmarks

vs. best public score
Scores inherited from Llama 3.2 3B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU63%
Multitask academic knowledge across 57 subjects. No source recorded yet.
MATH48%
High-school competition math problems. No source recorded yet.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • GPQA Main (0-shot)32.8%self-reported by Meta · no date on the source · Maker evaluation details identify this as the GPQA main set, not Diamond, 0-shot. Not comparable with the GPQA Diamond column, so shown here and never ranked.

More from Meta

See all 20 →

Price history

14 recorded changes
Recorded price changes for Llama 3.2 3B Instruct, newest first
DateRateWasNowChange
14 Nov 2026Input$0.0500$0.0509+1.8%
14 Nov 2026Output$0.3300$0.3350+1.5%
27 Jul 2026Input$0.0509$0.0500-1.8%
27 Jul 2026Output$0.3350$0.3300-1.5%
26 Jul 2026Output$0.3300$0.3350+1.5%
26 Jul 2026Input$0.0500$0.0509+1.8%
23 Jul 2026Input$0.0509$0.0500-1.8%
23 Jul 2026Output$0.3350$0.3300-1.5%
17 Jul 2026Input$0.0500$0.0509+1.8%
17 Jul 2026Output$0.3300$0.3350+1.5%
7 Jul 2026Output$0.3350$0.3300-1.5%
7 Jul 2026Input$0.0509$0.0500-1.8%

Rates per million tokens, as published by the provider or its router listing. Showing the 12 most recent of 14. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.

Frequently asked questions

How much does Llama 3.2 3B Instruct cost?

Llama 3.2 3B Instruct costs $0.0509 per million input tokens and $0.3350 per million output tokens, for a blended reference rate of $0.1361 per million tokens.

What is Llama 3.2 3B Instruct's context window?

Llama 3.2 3B Instruct supports up to 131,072 tokens of context in a single request.

What is Llama 3.2 3B Instruct best for?

Llama 3.2 3B Instruct is well suited to Runs on-device, Open weights and 128K context.

Who makes Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct is developed and served by Meta. It was released in Sep 2024.

Terms used on this page