Llama 3.2 3B Instruct

Meta's 3B-parameter text generation model, served through one OpenAI-compatible endpoint with transparent per-token pricing and project-scoped API keys.

MetaText Generation Model

Get started Documentation

MODEL SPEC

Developed by: Meta
Model family: Llama 3.2 3B Instruct
Size: 3B parameters
Architecture: Transformer
Context window: 131K tokens
Max output: 131K tokens
License: Provider license

Overview

Llama 3.2 3B Instruct is a 3B-parameter text generation model from Meta, available through the Inference.net serverless API. Use the same OpenAI-compatible request shape across the catalog and switch models by changing a single identifier.

The API supports streaming responses and project-scoped credentials. Usage, token volume, and spend appear in the dashboard automatically, so the model can move from evaluation to production without a second integration path.

QUICKSTARTGet API key

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.inference.net/v1',
  apiKey: process.env.INFERENCE_API_KEY,
})

const completion = await client.chat.completions.create({
  model: 'llama-3.2-3b-instruct',
  messages: [{ role: 'user', content: 'Hello' }],
})