All AI models · LLM benchmarks · Methodology

Amazon

Gemma 3 12B IT

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Model facts

Context window
128K tokens
Maximum output
131K tokens
Cheapest paid input
$0.05 per 1M tokens
Cheapest paid output
$0.15 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

tool calling, structured output, attachments, temperature control, open weights, text, image.

Local hardware estimate

At 4K context: Q4_K_M 8.4 GiB, Q8_0 14.1 GiB, F16 24.8 GiB working memory.

Parameters
12.2 billion
Architecture
gemma3
Model license
gemma

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.272 input / $0.272 output per 1M tokens
  • 2026-09-11: $0.05 input / $0.15 output per 1M tokens

API providers

  • Eden AI (Deep Infra) — model id deepinfra/google/gemma-3-12b-it; $0.05 input / $0.15 output per 1M tokens; provider documentation
  • Eden AI (Amazon Bedrock) — model id amazon/google.gemma-3-12b-it; $0.09 input / $0.29 output per 1M tokens; provider documentation
  • Eden AI (Amazon Bedrock, US) — model id amazon/google.gemma-3-12b-it@us; $0.09 input / $0.29 output per 1M tokens; provider documentation