Google: Gemma 4 12B IT

google/gemma-4-12B-it · rates as of 2026-09-20 · Benchmarks · AI plans · Calculator

Open Gemma instruction model for efficient chat and self-hosted deployments

Cheapest input

$0.05

$/MTok · models.dev

Cheapest output

$0.25

$/MTok

Context

131K

tokens

Sources

2 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates

Output $/MTok

↓ lowerOutput $0.3 → $0.252026-08-31
↓ lowerInput $0.06 → $0.052026-08-31
↑ higherOutput $0.25 → $0.32026-08-25
↓ lowerInput $0.25 → $0.062026-08-25

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

Source	Provider	Input	Output	Cache read	Context
models.devcheapestgemma-4-12b-it	NanoGPT	$0.05	$0.25	$0.025	131K
models.devgoogle/gemma-4-12B-it	Pioneer	$0.25	$0.25	$0.25	33K

Capabilities

Reasoning
Tool calling
Structured output
Attachments
Open weights
In: text
In: image
In: video
In: audio
Out: text

Released: 2026-08-01Family: gemma

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

Download for macOS

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.