All Meta models
M

Llama Guard 4 12B

Meta · released April 2025

Llama Guard 4 12B is a Meta model with a 164K token context window — about 230 pages of text. It reads Images and Text and replies in Text.

$0.207

input / 1M tokens

$0.207

output / 1M tokens

164K

context — about 230 pages

0.12¢

a client proposal

Pricing

Input
$0.207 per million tokens
Output
$0.207 per million tokens

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
Released
April 2025 (2025-04-30)
Context window
164K tokens — about 230 pages
Max output
16K tokens per reply
Input
Images and Text
Output
Text
Reasoning
Answers directly
Knowledge cutoff
2024-08-31

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$0.10$0.210 tokens250k500k750k1000k
Llama Guard 4 12B

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

Llama Guard 4 12B

Meta

0.05¢

for this task

80% input · 20% output

Full pricing →

Your $5 welcome credit covers about 9,661 of these.

Compare Llama Guard 4 12B

Closest in price on a typical task:

Questions, answered

How much does Llama Guard 4 12B cost on Alyph?

Llama Guard 4 12B costs $0.207 per million input tokens and $0.207 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.12¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is Llama Guard 4 12B's context window?

164K tokens — about 230 pages. Replies can be up to 16K tokens long.

Can Llama Guard 4 12B read images and files?

Llama Guard 4 12B reads Images and Text. Drop a file onto the canvas and it becomes part of the context — the only limit is the context window.

Does Llama Guard 4 12B show its reasoning?

No — Llama Guard 4 12B answers directly, without a visible thinking pass.

Test Llama Guard 4 12B against Hy3

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.