Gemma 3 4B (Pretrained)
Open Gemma instruction model for efficient chat and self-hosted deployments
Model facts
- Context window
- 33K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.15 per 1M tokens
- Cheapest paid output
- $0.15 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, temperature control, text.
Observed price history
- 2026-08-24: $0.15 input / $0.15 output per 1M tokens
API providers
- Pioneer — model id google/gemma-3-4b-pt; $0.15 input / $0.15 output per 1M tokens; provider documentation