Google logo

Gemma 3 12B


Gemma 3 12B is Google's language model with a 128K context window and up to 32K output tokens, starting at $0.150 / 1M input and $0.500 / 1M output. A 12-billion-parameter Gemma 3 open-weight LLM with multimodal vision-language input support.
Specifications
Canonical IDgoogle-gemma-3-12b
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window128K tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Parameters12B
Benchmarks
Intelligence Index
8.8
#410
Coding Index
6.3
#330
Math Index
18.3
#205
MMLU-Pro
0.6
#246
GPQA
0.3
#376
HLE
0.0
#295
LiveCodeBench
0.1
#277
AIME
0.2
#90
IFBench
0.4
#253
Time to First Token
SciCode
0.2
#350
MATH-500
0.9
#83
AIME 2025
0.2
#205
LCR
0.1
#299
TerminalBench Hard
0.0
#316
TAU2
0.1
#341
Output TPS
0.0
#360

Capabilities

Input1/5
Textβœ“
ImageΒ·
AudioΒ·
VideoΒ·
PDFΒ·
Output1/5
Textβœ“
ImageΒ·
AudioΒ·
VideoΒ·
EmbeddingΒ·
Capabilities0/13
ReasoningΒ·
Adaptive ReasoningΒ·
Function CallingΒ·
Parallel Function CallingΒ·
Structured OutputsΒ·
Native JSON SchemaΒ·
Web SearchΒ·
URL ContextΒ·
Computer UseΒ·
Code ExecutionΒ·
File SearchΒ·
Prompt CachingΒ·
Assistant PrefillΒ·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Databricks logo
Databricks
databricks/databricks-gemma-3-12b
$0.150$0.500

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 4 31Bβ€”β€”β€”β€”Available
Gemma 4 31Bβ€”β€”β€”β€”Available
Gemma 4 26B A4Bβ€”β€”β€”β€”Available
Gemma 4 26B A4Bβ€”β€”β€”β€”Available
Gemma 4 E4Bβ€”β€”β€”β€”Available
Gemma 4 E2Bβ€”β€”β€”β€”Available
Gemma 4 E4Bβ€”β€”β€”β€”Available
Gemma 4 E2Bβ€”β€”β€”β€”Available
Gemma 4β€”β€”β€”β€”Available
Gemma 4 31B IT Turboβ€”β€”β€”β€”Available
Gemma 3 12Bβ€”128K$0.150$0.500Current

Model IDs