All AI models · LLM benchmarks · Methodology

Meta

Llama 3.2 3B

Open Llama instruction model for multilingual chat, reasoning, and coding

Model facts

Context window
131K tokens
Maximum output
32K tokens
Cheapest paid input
$0.02 per 1M tokens
Cheapest paid output
$0.02 per 1M tokens
Open weights
yes
Providers
11

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, pdf.

Local hardware estimate

At 4K context: Q4_K_M 2.9 GiB, Q8_0 4.4 GiB, F16 7.2 GiB working memory.

Parameters
3.2 billion
Architecture
llama
Model license
llama3.2

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default3.9not measured3.3not measured

Observed price history

  • 2026-08-24: $0.02 input / $0.02 output per 1M tokens

API providers

  • Nvidia — model id meta/llama-3.2-3b-instruct; free input / free output per 1M tokens; provider documentation
  • Inference — model id meta/llama-3.2-3b-instruct; $0.02 input / $0.02 output per 1M tokens; provider documentation
  • NanoGPT — model id meta-llama/llama-3.2-3b-instruct; $0.031 input / $0.049 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id llama-3.2-3b-instruct; $0.03 input / $0.05 output per 1M tokens; provider documentation
  • NovitaAI — model id meta-llama/llama-3.2-3b-instruct; $0.03 input / $0.05 output per 1M tokens; provider documentation
  • Pioneer — model id meta-llama/Llama-3.2-3B; $0.1 input / $0.1 output per 1M tokens; provider documentation
  • Kilo Gateway — model id meta-llama/llama-3.2-3b-instruct; $0.05 input / $0.33 output per 1M tokens; provider documentation
  • OpenRouter — model id meta-llama/llama-3.2-3b-instruct; $0.05 input / $0.33 output per 1M tokens; provider documentation
  • Cloudflare Workers AI — model id @cf/meta/llama-3.2-3b-instruct; $0.051 input / $0.335 output per 1M tokens; provider documentation
  • Pioneer — model id meta-llama/Llama-3.2-3B-Instruct; $0.1 input / $0.335 output per 1M tokens; provider documentation
  • Venice AI — model id llama-3.2-3b; $0.15 input / $0.6 output per 1M tokens; provider documentation