Meta-llama

Llama 3.2 3B API Pricing 2026

Compare pricing, benchmarks, and providers for Llama 3.2 3B. 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. Pricing starts at $0.100 per million input tokens and $0.100 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$0.100
Output$0.100
Cached$0.050
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Text only

Llama 3.2 3B is priced at $0.100 per million input tokens and $0.100 per million output tokens. It has a context window of 131,072 tokens. It is available from 2 providers, with Fireworks the cheapest at $0.100 per million input tokens (input prices range from $0.100 to $0.150).

Pricing Comparison

Compare Llama 3.2 3B 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
$0.100
$0.100
—
—
—
131,072
Try
$0.100
$0.100
—
—
—
16,384
Try
$0.100
$0.200
—
—
—
65,536
Try
$0.100
$0.300
—
—
—
32,000
Try
$0.100
$0.300
—
—
—
32,768
Try
$0.100
$0.100
—
—
—
8,192
Try
$0.100
$0.100
—
—
—
32,768
Try
$0.100
$0.100
—
—
—
128,000
Try
$0.100
$0.100
—
—
—
131,072
Try
$0.100
$0.350
—
—
—
-
Try
$0.100
$0.100
—
—
—
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 is available from multiple providers with different pricing and availability.

2
Providers
$0.100
Cheapest Input/M
$0.100
Cheapest Output/M
Fireworks
Best Price

Provider Pricing

2 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
Fireworks
Fireworks
Best Price
$0.100
$0.100
$0.050
-
-
V
Vercel
$0.150
$0.150
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

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

Cost vs. Quality

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

X-axis:
Y-axis:
Loading chart...
Other models

Try Llama 3.2 3B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Llama 3.2 3B directly in your browser.

Open Playground

Frequently Asked Questions

Llama 3.2 3B costs $0.000100 per 1,000 input tokens and $0.000100 per 1,000 output tokens.
Llama 3.2 3B is available from 2 providers. Fireworks offers the best price.
Fireworks offers Llama 3.2 3B at $0.100 per million input tokens, the lowest of 2 providers (input prices range from $0.100 to $0.150 per million tokens).
We compare Llama 3.2 3B 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 →