Skip to content
LLMs
Meta Llama logo

Meta: Llama 3.2 3B Instruct

by Meta Llama

Meta: Llama 3.2 3B Instruct is a large language model from Meta Llama. It costs $0.050 per million input tokens and $0.330 per million output tokens. Its context window is 131K tokens.

Structured outputOpen weights
Input / 1M tokens
$0.050
Output / 1M tokens
$0.330
Cached input / 1M
-

Not supported

Context window
131K

tokens

Who serves it cheapest

2 hosts serve Llama 3.2 3B Instruct. Same weights, same API - the price difference is pure margin and routing.

Providers serving Meta: Llama 3.2 3B Instruct, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
ParasailCheapestbf16$0.050$0.330131K-99.9%
Cloudflare$0.051$0.33580K-99.3%

The spread between Parasail and Cloudflare is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

About Llama 3.2 3B Instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Specifications

Meta: Llama 3.2 3B Instruct specifications
Model IDmeta-llama/llama-3.2-3b-instruct
ProviderMeta Llama
Context window131K tokens
Max output118K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2023-12-31
Open weightsYes - meta-llama/Llama-3.2-3B-Instruct
ReleasedSeptember 25, 2024

Cheaper alternatives

Models that cost less than Llama 3.2 3B Instruct while keeping at least half its context window and every input modality it supports.

Qwen3.5-Flash

$0.065 in · $0.260 out

1.1× cheaper

Laguna S 2.1

$0.090 in · $0.180 out

1.1× cheaper

Qwen3.5-9B

$0.100 in · $0.150 out

1.1× cheaper

Nemotron 3.5 Lightning

$0.080 in · $0.200 out

1.1× cheaper

Granite 4.2 8B

$0.060 in · $0.250 out

1.1× cheaper

Frequently asked

How much does Meta: Llama 3.2 3B Instruct cost?

$0.050 per million input tokens and $0.330 per million output tokens.

What is the context window of Meta: Llama 3.2 3B Instruct?

131K tokens, with up to 118K tokens of output per request.

Which provider serves Meta: Llama 3.2 3B Instruct cheapest?

Parasail at $0.050 per million input tokens - about the same cheaper than Cloudflare, the most expensive of the 2 hosts serving it.