All AI models · LLM benchmarks · Methodology

Google

Gemma 4 12B Instruct

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.

Model facts

Context window
262K tokens
Maximum output
33K tokens
Cheapest paid input
$0.05 per 1M tokens
Cheapest paid output
$0.25 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, structured output, attachments, open weights, text, image, audio, video.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning22.231.0not measured131.1
Non-reasoning13.2not measurednot measured132.7

Observed price history

  • 2026-08-24: $0.06 input / $0.3 output per 1M tokens
  • 2026-08-31: $0.05 input / $0.25 output per 1M tokens

API providers