# Qwen/Qwen3.5-4B

> Qwen/Qwen3.5-4B is an open-weight language model from Alibaba (Qwen), released on 3 Mar 2026. It accepts text, images and video and generates text, with a 262K-token context window and up to 66K output tokens per response.

Source page: https://www.aimodel.directory/models/qwen3-5-4b
Last verified: 21 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 3 Mar 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Knowledge cutoff:** Apr 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Input:** Text, images and video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/siliconflow-cn/models/Qwen/Qwen3.5-4B.toml)

## API pricing (USD per 1M tokens)

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

## FAQ

### What is the context window of Qwen/Qwen3.5-4B?

Qwen/Qwen3.5-4B has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.

### Is Qwen/Qwen3.5-4B open source?

Qwen/Qwen3.5-4B is an open-weight model. Check the license terms before commercial use.

### When was Qwen/Qwen3.5-4B released?

Alibaba (Qwen) released Qwen/Qwen3.5-4B on 3 Mar 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen/Qwen3.5-4B", https://www.aimodel.directory/models/qwen3-5-4b