Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Pricing
- Input Tokens: $0.140 /M tokens
- Output Tokens: $0.400 /M tokens
- Cache Read: $0.000 /M tokens
Input Modalities
Output Modalities
- Text
Try this model
Python
