All AI models · LLM benchmarks · Methodology

Meta

Llama 3.2 1B

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

Model facts

Context window
6K tokens
Maximum output
6K tokens
Cheapest paid input
$0.01 per 1M tokens
Cheapest paid output
$0.01 per 1M tokens
Open weights
yes
Providers
7

Capabilities and modalities

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

Local hardware estimate

At 4K context: Q4_K_M 1.7 GiB, Q8_0 2.3 GiB, F16 3.4 GiB working memory.

Parameters
1.2 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
default1.0not measured0.0not measured

Observed price history

  • 2026-08-24: $0.01 input / $0.01 output per 1M tokens

API providers

  • Nvidia — model id meta/llama-3.2-1b-instruct; free input / free output per 1M tokens; provider documentation
  • Inference — model id meta/llama-3.2-1b-instruct; $0.01 input / $0.01 output per 1M tokens; provider documentation
  • Pioneer — model id meta-llama/Llama-3.2-1B; $0.1 input / $0.1 output per 1M tokens; provider documentation
  • Cloudflare Workers AI — model id @cf/meta/llama-3.2-1b-instruct; $0.027 input / $0.201 output per 1M tokens; provider documentation
  • Kilo Gateway — model id meta-llama/llama-3.2-1b-instruct; $0.027 input / $0.201 output per 1M tokens; provider documentation
  • OpenRouter — model id meta-llama/llama-3.2-1b-instruct; $0.027 input / $0.201 output per 1M tokens; provider documentation
  • Pioneer — model id meta-llama/Llama-3.2-1B-Instruct; $0.1 input / $0.201 output per 1M tokens; provider documentation