# DiffusionGemma 26B A4B IT

> DiffusionGemma 26B A4B IT is an open-weight language model from Google DeepMind, released on 9 Jun 2026. It accepts text and images and generates text, with a 250K-token context window and up to 33K output tokens per response.

Source page: https://www.aimodel.directory/models/diffusiongemma-26b-a4b-it
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 9 Jun 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Context window:** 250K (250,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Max output:** 33K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/diffusiongemma-26b-a4b-it.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | 250K |

## FAQ

### What is the context window of DiffusionGemma 26B A4B IT?

DiffusionGemma 26B A4B IT has a context window of 250,000 tokens (250K) and can generate up to 32,768 tokens in a single response, according to models.dev.

### Is DiffusionGemma 26B A4B IT open source?

DiffusionGemma 26B A4B IT is an open-weight model. Check the license terms before commercial use.

### When was DiffusionGemma 26B A4B IT released?

Google DeepMind released DiffusionGemma 26B A4B IT on 9 Jun 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "DiffusionGemma 26B A4B IT", https://www.aimodel.directory/models/diffusiongemma-26b-a4b-it