Gemma 3 12B

GOOGLE Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1054Chatbot Arena Verified

Max Context Limit131,072Max Out: 16,384 tokens

Prompt CachingStandardNo Cache Discount

Standard API / 1M$0.20🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Vision
Reasoning
🧠 Extended Test-Time Reasoning

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,...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.05 / 1M

Output Tokens (Completion)$0.15 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupGemma 3 12B vs OpenAI: GPT-6 Luna (batch)VS Engine MatchupGemma 3 12B vs OpenAI: gpt-oss-120b (batch)VS Engine MatchupGemma 3 12B vs Meta: Llama Guard 4 12B VS Engine MatchupGemma 3 12B vs Meta: Muse Spark 1.2 Contributor VS Engine MatchupGemma 3 12B vs NVIDIA: Nemotron 3.5 Content Safety (free)VS Engine MatchupGemma 3 12B vs Reka Edge