# Qwen: Qwen3 Embedding 8B

> Qwen's 8B embedding model for high-quality semantic search, clustering and retrieval in many languages, with inputs of up to 32k tokens.

- Model ID: `qwen/qwen3-embedding-8b`
- Maker: Qwen (`qwen`)
- Context length: 32,768 tokens
- Input: text
- Output: embeddings
- Capabilities: -
- Page: https://tokenlane.de/models/qwen/qwen3-embedding-8b

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| TensorX | IE, FI | no | yes |
| Lyceum | FR, FI, DE | no | yes |
| OVHcloud | FR | yes | yes |
| Scaleway | FR | yes | no |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/embeddings.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
