# Gemma 3 4B IT

> Gemma 3 4B IT is an open-weight language model from Google DeepMind, released on 12 Mar 2025. It accepts text and images and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.04 per million input tokens and $0.08 per million output tokens (Amazon Bedrock), across 5 providers we track.

Source page: https://www.aimodel.directory/models/gemma-3-4b-it
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 12 Mar 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/google/gemma-3-4b-it)
- **License:** gemma (source: Hugging Face, https://huggingface.co/google/gemma-3-4b-it)
- **Parameters:** 4.3B (source: Hugging Face, https://huggingface.co/google/gemma-3-4b-it)
- **Context window:** 131K (131,072 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Knowledge cutoff:** Aug 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-4b-it.toml)
- **Hugging Face:** google/gemma-3-4b-it (source: Hugging Face, https://huggingface.co/google/gemma-3-4b-it)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | 131K |
| Amazon Bedrock | $0.04 | $0.08 | – | 131K |
| DeepInfra | $0.05 | $0.10 | – | 131K |
| Hugging Face Inference Providers | $0.05 | $0.10 | – | 131K |
| OpenRouter | $0.05 | $0.10 | – | 131K |

## FAQ

### What is the context window of Gemma 3 4B IT?

Gemma 3 4B IT has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.

### How much does the Gemma 3 4B IT API cost?

Gemma 3 4B IT is listed from $0.04 per million input tokens and $0.08 per million output tokens (Amazon Bedrock). Prices last verified 4 Oct 2026.

### Is Gemma 3 4B IT open source?

Gemma 3 4B IT is an open-weight model: its weights are published on Hugging Face as google/gemma-3-4b-it under the gemma license. Check the license terms before commercial use.

### When was Gemma 3 4B IT released?

Google DeepMind released Gemma 3 4B IT on 12 Mar 2025, according to models.dev.

### Which providers offer Gemma 3 4B IT?

We track Gemma 3 4B IT on 5 providers: NVIDIA NIM, Amazon Bedrock, DeepInfra, Hugging Face Inference Providers, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Gemma 3 4B IT", https://www.aimodel.directory/models/gemma-3-4b-it