GoogleactiveOpen Source

Gemma 3 12B

gemma-3-12b

Efficient 12B open model balancing quality and resource requirements.

Context Window

131.1K

tokens

Max Output

8.2K

tokens

Input Price

—

per 1M tokens

Output Price

—

per 1M tokens

Details

Familygemma

Parameters12B

Training Cutoff2024-12-01

ReleasedMarch 12, 2025

Capabilities

VisionStreamingCodeMultimodal

Documentation

Evaluation Scores(2 benchmarks)

HumanEvalFunction-level Python code generation

55%

MMLU-ProHarder successor to MMLU

42.5%

Quick Access

curl pikaainews.com/api/models/google-gemma-3-12b

npx pika-models info google-gemma-3-12b

Get API Access

Official

Google AI Studio

Official Gemini API. Free tier available.

Third-Party Providers & Aggregators

DeepInfra

Lowest per-token rates for open-source models.

Fireworks AI

Fastest inference engine. Multimodal support, HIPAA/SOC2.

Groq

Ultra-fast LPU inference. Best latency for real-time apps.

OpenRouter

500+ models, one API key. Pay-per-token, no minimums.

Together AI

Fast open-source model inference. Sub-100ms latency.

Other gemma models

Google

Gemma 3 4B

gemma-3-4b

131.1K ctx

Google

Gemma 3 1B

gemma-3-1b

32.8K ctx

Google

Gemma 3 27B

gemma-3-27b

131.1K ctx