---
id: "meta-llama/llama-3.2-3b-instruct"
also: ["meta-llama/llama-3.2-3b-instruct", "meta-llama/Llama-3.2-3B-Instruct"]
cheapest_list_usd_per_m: "0.05 in, 0.33 out, at parasail/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.0478 in, 0.328 out, at parasail/bf16 on openrouter"
context: 131072
max_output: 117964
input: ["text"]
output: ["text"]
released: "2024-09-25"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Meta: 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...