Meta-llama

Llama 3.2 3B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Llama 3.2 3B Instruct. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Llama 3.2 3B Instruct was released on September 25, 2024. Pricing starts at $0.030 per million input tokens and $0.050 per million output tokens. The model supports a context window of up to 80K tokens. API access is available through Meta-llama.

Context Window
80K
tokens
Pricing
Input$0.030
Output$0.050
Cached$0.050
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

Llama 3.2 3B Instruct is priced at $0.030 per million input tokens and $0.050 per million output tokens. It has a context window of 80,000 tokens. It is available from 5 providers, with Novita the cheapest at $0.030 per million input tokens (input prices range from $0.030 to $0.100). On benchmarks, Llama 3.2 3B Instruct scores Intelligence 24.2 (36th percentile), MMLU Pro 24.4 (23rd percentile), GPQA 3.8 (10th percentile).

Pricing Comparison

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

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.030
$0.050
—
24.4
3.8
80,000
Try
$0.020
$0.020
—
—
—
32,768
Try
$0.020
$0.096
—
—
74.3
1,000,000
Try
$0.021
$0.063
—
—
—
262,144
Try
$0.025
$0.100
—
—
—
262,144
Try
$0.025
$0.200
—
—
—
400,000
Try
$0.025
$0.100
—
—
—
262,144
Try
$0.028
$0.110
—
—
—
32,768
Try
$0.030
$0.100
—
—
—
131,072
Try
$0.030
$0.120
—
—
—
32,768
Try
$0.030
$0.120
—
—
—
32,768
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.

5
Providers
$0.030
Cheapest Input/M
$0.050
Cheapest Output/M
Novita
Best Price

Provider Pricing

5 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Novita
Novita
Best Price
$0.030
$0.050
-
-
-
$0.050
$0.330
-
-
100.0%
$0.050
$0.330
-
-
-
$0.060
$0.060
-
-
-
$0.100
$0.100
$0.050
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Llama 3.2 3B Instruct perform? Vote based on your experience.

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
24.2 (36th pct)
Coding
-
Math
-
MMLU Pro
24.4 (23rd pct)
GPQA
3.8 (10th pct)
LiveCodeBench
-
AIME
-
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

Frequently Asked Questions

Llama 3.2 3B Instruct costs $0.000030 per 1,000 input tokens and $0.000050 per 1,000 output tokens.
Llama 3.2 3B Instruct is available from 5 providers. Novita offers the best price.
Novita offers Llama 3.2 3B Instruct at $0.030 per million input tokens, the lowest of 5 providers (input prices range from $0.030 to $0.100 per million tokens).
Llama 3.2 3B Instruct scores Intelligence 24.2 (36th percentile), MMLU Pro 24.4 (23rd percentile), GPQA 3.8 (10th percentile). Only benchmarks with published data for this model are shown.
We compare Llama 3.2 3B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Meta-llama Models

See pricing for all Meta-llama models.

View all Meta-llama models →