All Models

Gemma 3 27B

gemma Tool Calling Attachments Open Weights Structured Output

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, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Providers 4
Released Mar 12, 2025
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

10.3
Intelligence Index
9.6
Coding Index
20.7
Math Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Privatemode AI gemma-3-27b $0.00/MTok $0.00/MTok 128K 8.2K
OpenRouter google/gemma-3-27b-it $0.04/MTok $0.15/MTok 96K 96K
NovitaAI google/gemma-3-27b-it $0.12/MTok $0.20/MTok 98.3K 16.4K
STACKIT google/gemma-3-27b-it $0.49/MTok $0.71/MTok 37K 8.2K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output