# Gemma 4 E4B IT

> Gemma 4 E4B IT is an open-weight language model from Google DeepMind, released on 2 Apr 2026. It accepts text, images and audio and generates text, with a 33K-token context window and up to 33K output tokens per response.

Source page: https://www.aimodel.directory/models/gemma-4-e4b-it
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 2 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Max output:** 33K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Input:** Text, images and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/google/gemma-4-E4B-it.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Gemma 4 E4B IT?

Gemma 4 E4B IT has a context window of 32,768 tokens (33K) and can generate up to 32,768 tokens in a single response, according to models.dev.

### Is Gemma 4 E4B IT open source?

Gemma 4 E4B IT is an open-weight model. Check the license terms before commercial use.

### When was Gemma 4 E4B IT released?

Google DeepMind released Gemma 4 E4B IT on 2 Apr 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Gemma 4 E4B IT", https://www.aimodel.directory/models/gemma-4-e4b-it