Integrate multimodal vision capabilities using Gemma 3 12B IT, designed to process both text and images seamlessly. This model delivers cost-effective pricing at $0.05/1M input and $0.15/1M output tokens, native tool calling support, open weights architecture. Access Gemma 3 12B IT via the Hugging Face API with up to 131K output tokens.
Tokens
Tokens
Tokens
Gemma 3 12B IT by Hugging Face costs $0.05 per 1M input tokens and $0.15 per 1M output tokens.