Context window
256,000 tokens
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
LLM · Google
Google's 2 April 2026 Gemma 4 post releases four sizes under an Apache 2.0 license and says the weights can be downloaded from Hugging Face, Kaggle, or Ollama. It describes the 31B model as dense. It says the larger models offer up to a 256K context window. The post does not publish a token price.
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
256,000 tokens
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
No first-party API price
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
No first-party API price
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
Not published
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
Yes
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
Not published
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
Apache 2.0
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
Not published
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
31B
Checked 19 Oct 2026https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/