Google

Google: Gemma 4 31B

google/gemma-4-31b-it

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.

  • Context window: 262,144 tokens
  • Input: image, text, video
  • Output: text
  • Pricing: $0.12/M input tokens, $0.37/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.