# Qwen 3 Embedding 4B

Multilingual text embedding model with truncatable dimensions for retrieval and RAG. Input longer than the context length is rejected with a 400 (context_length_exceeded).

Model id: `qwen3-embedding-4b`
Context: 32K tokens
Quantization: fp16
Regions: SJC
Hugging Face: [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B)

## Pricing

- Tokens: $0.05 / 1M tokens

## Inputs

- text: context 32K tokens

## Output: embeddings

| Parameter | Type | Values | Default |
| --- | --- | --- | --- |
| `encoding_format` | string | float, base64 |  |
| `dimensions` | integer | at least 1 |  |
| `input_type` | string | search_query, search_document |  |

## Endpoints

- [`POST /v1/embeddings`](/docs/reference/create-embeddings.md): Create Embeddings