Google: Gemma 4 31B

google/gemma-4-31b-it

Released Apr 2, 2026262,144 context

$0.14/M input tokens$0.40/M output tokens

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.

Google: Gemma 4 31B

google/gemma-4-31b-it

Released Apr 2, 2026262,144 context

$0.14/M input tokens$0.40/M output tokens

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.

Recent activity on Gemma 4 31B

Total usage per day on OpenRouter

Prompt

400M

Completion

73.6M

Reasoning

14.5M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.