Model specification · Google

Gemma 3 12B

google/gemma-3-12b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

SpecificationsReported values
Context window
131K
Maximum output
16K
Architecture
text+image->text
Tokenizer
Gemini
Knowledge cutoff
2024-08-31
Moderated
No
Input modalities
text image
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.050 / M
Output$0.150 / M
Benchmark indexesReported indexes
Intelligence
5.5
Coding
5.8
Agentic
0.3
Design Arena Elo
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00065
Long analysis100K / 4K × 150%$0.00560
Workday20K / 2K × 1,00030%$1.30
More from GoogleAll Google models
ModelContextInput / MOutput / MIntel.
Gemini 3.5 Flash1.0M$1.50$9.0050.2
Gemini 3.6 Flash1.0M$1.50$7.5050.1
Gemini 3.1 Pro Preview1.0M$2.00$12.0046.5
Gemini 3.5 Flash Lite1.0M$0.300$2.5036.5
Gemma 4 31B262K$0.100$0.34029.4
Gemini 2.5 Pro1.0M$1.25$10.0025.8
Gemma 4 26B A4B 262K$0.070$0.34025.7
Gemini 3.1 Flash Lite Preview1.0M$0.250$1.5025
Gemma 3 27B262K$0.080$0.4507.4