# Qwen 3 Embedding 4B

> Qwen 3 Embedding 4B is an open-weight language model from Alibaba (Qwen), released on 5 Jun 2025. It accepts text and generates text, with a 33K-token context window and up to 2K output tokens per response. As of 21 Oct 2026, the lowest listed API price is $0.01 per million input tokens and Free per million output tokens (Hugging Face Inference Providers), across 2 providers we track.

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

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 5 Jun 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Max output:** 2K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Knowledge cutoff:** Dec 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Embedding-4B.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Hugging Face Inference Providers | $0.01 | Free | – | 33K |
| Vercel AI Gateway | – | – | – | 33K |

## FAQ

### What is the context window of Qwen 3 Embedding 4B?

Qwen 3 Embedding 4B has a context window of 32,768 tokens (33K) and can generate up to 2,048 tokens in a single response, according to models.dev.

### How much does the Qwen 3 Embedding 4B API cost?

Qwen 3 Embedding 4B is listed from $0.01 per million input tokens and Free per million output tokens (Hugging Face Inference Providers). Prices last verified 21 Oct 2026.

### Is Qwen 3 Embedding 4B open source?

Qwen 3 Embedding 4B is an open-weight model. Check the license terms before commercial use.

### When was Qwen 3 Embedding 4B released?

Alibaba (Qwen) released Qwen 3 Embedding 4B on 5 Jun 2025, according to models.dev.

### Which providers offer Qwen 3 Embedding 4B?

We track Qwen 3 Embedding 4B on 2 providers: Hugging Face Inference Providers, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen 3 Embedding 4B", https://www.aimodel.directory/models/qwen3-embedding-4b