gemma-4-31b-it-free

by Google

Gemma 4 31B Instruct is a 30.7B dense multimodal model developed by Google DeepMind that supports both text and image inputs with text outputs. It features an expansive 256K token context window alongside a configurable thinking and reasoning mode. The model also includes native function support to streamline complex tasks.

Specifications

Context window262,144 tokens
Modalitiestext, image
Featuresreasoning, tool_calling, long_context
Endpointschat_completions

Paid version: gemma-4-31b-it

More from Google

Use gemma-4-31b-it-free via the AIHubMix unified API — one interface for every major LLM.