> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen3 Embedding 4B

> 2560-dimension embeddings — the middle of the Qwen3 retrieval line by recall, not by price. The 8B is both better and cheaper; this SKU costs twice as much per million tokens. Reach for the 4B only when the index is already fixed at 2560 dimensions.

## Overview

2560-dimension embeddings — the middle of the Qwen3 retrieval line by recall, not by price. The 8B is both better and cheaper; this SKU costs twice as much per million tokens. Reach for the 4B only when the index is already fixed at 2560 dimensions.

## Specs

| Field | Value |
| - | - |
| Model ID | `qwen3-embedding-4b` |
| Best for | Existing 2560-dimension indexes |
| Context window | 32,768 |
| Input modalities | Text |
| Output modalities | Text |
| Speed | Medium |
| Cost band | Cheap |
| Release stage | Stable |

## Pricing

| | Per 1M tokens |
| - | :-: |
| Input | \$0.027 |
| Output | \$0.00 |

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.embeddings.create(
    model="qwen3-embedding-4b",
    input=["first document", "second document"],
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=search-documents&quality_tier=strong"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.