All AI models · LLM benchmarks · Methodology

Gemma 2

Open Gemma instruction model for efficient chat and self-hosted deployments

Model facts

Context window
8K tokens
Maximum output
8K tokens
Cheapest paid input
$0.01 per 1M tokens
Cheapest paid output
$0.03 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

temperature control, text.

Observed price history

  • 2026-08-24: $0.01 input / $0.03 output per 1M tokens

API providers