Google logo

Gemma 3 12B


Gemma 3 12B is Google logoGoogle's language model with a 33K context window and up to 8K output tokens, available from 3 providers. An instruction-tuned 12B Gemma 3 open LLM supporting vision-language input, 128k context, and over 140 languages.
Spec
Canonical IDgoogle-gemma-3-12b-instruct
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window33K tokens
Max Output8K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters12B
Release Date · 1 year ago

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
$0.050$0.100
Novita logo
Novita
$0.050$0.100
Amazon Bedrock logo
Amazon Bedrock
$0.090$0.290$0.050$0.150$0.050$0.150$0.160$0.510

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 3 12B33KCurrent
Gemma 3 27B Instruct131KAvailable
Gemma 3 27B IT131K$0.060$0.160Available

Model IDs