Llama 3.2 3B Instruct API Pricing 2026

Overview

Llama 3.2 3B Instruct was released on September 25, 2024. Pricing starts at $0.020 per million input tokens and $0.020 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Meta-llama.

Context Window

131K

tokens

Pricing

Input$0.020

Output$0.020

per 1M tokens

Speed

Output84 tok/s

TTFT0.62s

median latency

Capabilities

Tools

Pricing Comparison

Compare Llama 3.2 3B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Context	Actions
M Meta-llama	llama-3.2-3b-instruct	$0.020	$0.020	131,072	Try
LQ Liquid	lfm2-8b-a1b	$0.010	$0.020	32,768	Try
LQ Liquid	lfm-2.2-6b	$0.010	$0.020	32,768	Try
I Ibm-granite	granite-4.0-h-micro	$0.017	$0.110	131,000	Try
G Google	gemma-3-4b-it	$0.017	$0.068	96,000	Try
MI Nousresearch	deephermes-3-mistral-24b-preview	$0.020	$0.100	32,768	Try
O OpenAI	gpt-oss-20b	$0.020	$0.100	131,072	Try
G Google	gemma-3n-e4b-it	$0.020	$0.040	32,768	Try
M Meta-llama	llama-guard-3-8b	$0.020	$0.060	131,072	Try
M Meta-llama	llama-3.1-8b-instruct	$0.020	$0.050	16,384	Try
MI Mistral AI	mistral-nemo	$0.020	$0.040	131,072	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Llama 3.2 3B Instruct is available from multiple providers with different pricing and availability.

6

Providers

$0.020

Cheapest Input/M

$0.020

Cheapest Output/M

DeepInfra

Best Price

Provider Pricing

6 models

Provider	Input $/M	Output $/M	Uptime
D DeepInfra Best Price	$0.020	$0.020	100.0%
N Novita	$0.030	$0.050	100.0%
C Cloudflare	$0.051	$0.340	100.0%
T Together	$0.060	$0.060	100.0%
H Hyperbolic	$0.100	$0.100	-
OpenRouter	$N/A	$N/A	-

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare Llama 3.2 3B Instruct's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

Llama 3.2 3B Instruct

Other models

Detailed Benchmark Scores

Intelligence

9.7 (7th pct)

Coding

-

Math

3.3 (4th pct)

MMLU Pro

34.7 (6th pct)

GPQA

25.5 (9th pct)

LiveCodeBench

8.3 (3th pct)

AIME

6.7 (10th pct)

Aider

-

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Llama 3.2 3B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Llama 3.2 3B Instruct directly in your browser.

Open Playground