Skip to main content
MetaOct 3, 2024

Llama 3.2 3B

llama-3.2-3bPrivateOpen weights

Llama 3.2 3B is a lightweight model from Meta’s Llama 3.2 family, sized for fast, low-cost tasks such as summarization, classification and rewriting. It supports text input and output with a 128K-token context window and handles several languages.

$0.15/$0.60
per 1M in / out
128K
context window
4K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 25%73.2%
Blended pricecheaper than 86%$0.26
Context windowlarger than 2%128K
Max outputlarger than 0%4K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText
Streamingstream: true
Function callingtools
Web searchenable_web_search

Not supportedstructured outputs, reasoning, image input, video input, audio input, X search, prompt caching and log probabilities

Benchmarks

GPQA Diamond
73.2%104th of 139 · 10 score higher for less, including GPT-6 Luna, DeepSeek V4 Flash 0423 and Google Gemma 4 31B Instruct

Specs

Model ID
llama-3.2-3b
Endpoint
POST /api/v1/chat/completions
Context window
128,000 tokens
Max output
4,096 tokens
Reasoning
None
Precision
FP16
Privacy
Private
Added
Oct 3, 2024

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Llama 3.2 3B$0.15$0.6073.2%128K4K——
Qwen 3 235B A22B Instruct 2507$0.15$0.7550.5%128K16K——
GPT-4o Mini$0.15$0.6040.4%128K16K——
OpenAI GPT OSS 120B E2EE$0.13$0.6562.6%128K32K——
DeepSeek V3.2$0.33$0.4886.9%160K32K——

Other versions

  1. Llama 3.2 3BOct 2024
  2. Llama 3.3 70BApr 2025

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.15per 1M tokens
Output$0.60per 1M tokens

Estimate a workload

$0.0006per request
$6.00for 10,000 requests

Blended price against similar models

Llama 3.2 3B$0.2625

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.2-3b",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelllama-3.2-3bRequired
messagestextContent parts the model reads
max_completion_tokensUp to 4,096
toolsFunction definitionsWith tool_choice
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations