Meta: Llama-3.2-3B

Small open Llama base model for lightweight text generation and self-hosting

Model lab: Meta
Model family: llama

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output8,192

InputUSD 0.08 / 1M tokens

OutputUSD 0.08 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to meta/llama-3.2-3b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "meta/llama-3.2-3b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Llama-3.2-3B API Pricing

Type	Price information
Input	USD 0.08 / 1M tokens
Output	USD 0.08 / 1M tokens
Cached input	USD 0.08 / 1M tokens
Cache write	USD 0.08 / 1M tokens

Performance

Performance trends

Throughput91.8 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current91.8 tok/s

Window average89.3 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current13.2 s

Window average16.4 s

Prompt cache hit rate

Current26.4%

Window average24.3%

Error rate

Current0.0%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Llama-3.2-3B Compare models

Model	Input price	Output price	Context window	Capabilities
Llama-3.2-3BThis page	USD 0.08 / 1M tokens	USD 0.08 / 1M tokens	131,072	Text output
Llama-3.3-70B-Instruct	USD 0.08 / 1M tokens	USD 0.256 / 1M tokens	128,000	Text output · Tool calling
Llama-3.2-1B	USD 0.08 / 1M tokens	USD 0.08 / 1M tokens	131,072	Text output
Llama 3.2 1B Instruct	USD 0.0216 / 1M tokens · Context ≤ 60000 tokens · Maximum output 32000 tokens	USD 0.1608 / 1M tokens · Context ≤ 60000 tokens · Maximum output 32000 tokens	131,072	Text output · Tool calling
Llama-3.1-8B-Instruct	USD 0.016 / 1M tokens	USD 0.032 / 1M tokens	128,000	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 131,072
Maximum output: 8,192
Release date: 2024-09-25
Attachments: No
Reasoning: No
Tool calling: No
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Llama-3.2-3B for?

Small open Llama base model for lightweight text generation and self-hosting

What inputs and outputs does Llama-3.2-3B support?

Recorded inputs: text; outputs: text.

How is Llama-3.2-3B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.08 / 1M tokens; Output USD 0.08 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Llama-3.2-3B?

Current model records list Context window 131,072 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses meta/llama-3.2-3b. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.