meta/llama-3.2-3b-instruct — Free API

Created by Meta ⭐ Score: 43 Verified
nvidia-nim/meta-llama-3-2-3b-instruct
chat
Get API key → Save Key to Vault Test in Playground →

What is meta/llama-3.2-3b-instruct?

Llama 3.2 3B Instruct is Meta's compact instruction model, free on NVIDIA NIM with up to 40 RPM and no daily token cap. At 3B parameters, it balances efficiency and capability — suitable for lightweight chat, text classification, and as a fast baseline for prompt testing. OpenAI-compatible API. Requires free NVIDIA Developer Program membership and phone verification.

Model ID
meta/llama-3.2-3b-instruct
Base URL
https://integrate.api.nvidia.com/v1

meta/llama-3.2-3b-instruct API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="meta/llama-3.2-3b-instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://integrate.api.nvidia.com/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "meta/llama-3.2-3b-instruct",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);
curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "meta/llama-3.2-3b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from NVIDIA NIM

01-ai/yi-large

131K ctx · No card

adept/fuyu-8b

131K ctx · No card

ai21labs/jamba-1.5-large-instruct

131K ctx · No card

aisingapore/sea-lion-7b-instruct

131K ctx · No card

baai/bge-m3

131K ctx · No card

bigcode/starcoder2-15b

131K ctx · No card

More About NVIDIA NIM

How to get an API key, rate limits, platform limitations, and tool configuration — everything you need to set up NVIDIA NIM as a free LLM API backend.

View NVIDIA NIM full guide →