All AI models · LLM benchmarks · Methodology

Pearl AI Gemma 4 31B Instruct

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

Model facts

Context window
32K tokens
Maximum output
32K tokens
Cheapest paid input
$0.28 per 1M tokens
Cheapest paid output
$0.86 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, temperature control, text.

Observed price history

  • 2026-08-24: $0.28 input / $0.86 output per 1M tokens

API providers

  • Together AI — model id pearl-ai/gemma-4-31b-it; $0.28 input / $0.86 output per 1M tokens; provider documentation