All Google models

Gemma 3 12B

Google · released March 2025

Gemma 3 12B is a Google model with a 131K token context window — about 190 pages of text. It reads Text and Images and replies in Text.

$0.058

input / 1M tokens

$0.172

output / 1M tokens

131K

context — about 190 pages

0.04¢

a client proposal

Pricing

Input
$0.058 per million tokens
Output
$0.172 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
March 2025 (2025-03-13)
Context window
131K tokens — about 190 pages
Max output
16K tokens per reply
Input
Text and Images
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$0.080 tokens250k500k750k1000k
Gemma 3 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.

Gemma 3 12B

Google

0.02¢

for this task

57% input · 43% output

Full pricing →

Your $5 welcome credit covers about 24,844 of these.

Compare Gemma 3 12B

Closest in price on a typical task:

Questions, answered

How much does Gemma 3 12B cost on Alyph?

Gemma 3 12B costs $0.058 per million input tokens and $0.172 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.04¢. 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 Gemma 3 12B's context window?

131K tokens — about 190 pages. Replies can be up to 16K tokens long.

Can Gemma 3 12B read images and files?

Gemma 3 12B reads Text and Images. Drop a file onto the canvas and it becomes part of the context — the only limit is the context window.

Does Gemma 3 12B show its reasoning?

No — Gemma 3 12B answers directly, without a visible thinking pass.

Test Gemma 3 12B against Qwen3 30B A3B Instruct 2507

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