NVIDIA

Llama 3.2 3B Instruct — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCENVIDIA
Input Cost
$0.05/1M
Output Cost
$0.33/1M
Context Window
131K
Max Output
32K
Accepts
text

Llama 3.2 3B Instruct by NVIDIA demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Reasoning Benchmarks

GPQA Diamond
11.6%139th of 140

Graduate-level science Q&A by domain experts

Papers

Cost Benchmarks

Output Cost
$0.33139th of 413

Cost per 1M output tokens

OpenRouter API
Input Cost
$0.0588th of 413

Cost per 1M input tokens

OpenRouter API

Context Benchmarks

Context Length
131K212th of 451

Maximum context window size

OpenRouter API

Available from 9 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 2 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Nvidia$0$033K
Inference$0.02$0.0216K
DevPass (LLM Gateway)$0.03$0.0533K
LLM Gateway$0.03$0.0533K
NovitaAI$0.03$0.0533K
NanoGPT$0.0306$0.0493$0.0153131K
OpenRouter$0.05$0.33131KSupported
Cloudflare Workers AI$0.0509$0.33580KSupported
Pioneer$0.1$0.335$0.1131K

Llama 3.2 3B Instruct — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Llama 3.2 3B Instruct — Frequently Asked Questions

How much does Llama 3.2 3B Instruct cost?

Llama 3.2 3B Instruct costs $0.05 per 1M input tokens and $0.33 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct was created by NVIDIA. It is classified as a open source model in our catalogue.

Is Llama 3.2 3B Instruct open source?

Yes, Llama 3.2 3B Instruct is an open-source model. The model weights are publicly available for download and self-hosting.