Gemma 4
Open (Apache 2.0) family of multimodal AI models from Google DeepMind (E2B/E4B/26B A4B/31B). Supports text, image, audio, and video. Native function calling.
Technical specification
Modalities
Capabilities
12Coding★
Coding
Multilingual★
Language
Multi-step reasoning★
Reasoning
Long context★
Reasoning
Structured output★
Structured gen.
Image understanding★
Vision
Audio understanding
Audio
Multimodal understanding★
Multimodality
Reasoning★
Reasoning
Video Understanding
Other
Function Calling
Planning
Interleaved Multimodal Input
Reasoning
Model weights available free of charge (Apache 2.0). Access via Gemini Developer API includes a free tier. Commercial deployment on Vertex AI is billed at standard Google Cloud rates.
Public pricing is marked but no items (e.g. price per 1M tokens) have been added yet.
Security and enterprise
Gemma 4 model card includes safety evaluation results. As an open-source model, deployment responsibility lies with the user. Documentation on responsible AI use is available.
Technical information
Gemma 4 is an open-source model (Apache 2.0). Production deployments require independent risk assessment. Google publishes a model card with safety evaluation results.