Ce que cette page répond
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilitie
- Google · google/gemma-3-4b-it
- text+image->text · route modèle globale
- 131 072 context · 0,04 $US input