All Models

Gemma 4 12B Instruct

gemma Tool Calling Attachments Open Weights Structured Output

Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.

Providers 1
Released Aug 1, 2026
Input Modalities text, image, video, audio
Output Modalities text
Tarsk Use coding

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT gemma-4-12b-it $0.06/MTok $0.30/MTok 262.1K 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output