Qwen3-Embedding-8B
Leading open-weight multilingual embedding model.
Qwen3-Embedding-8B is part of the Qwen3 Embedding series for text embedding and ranking, inheriting Qwen3’s multilingual and long-text understanding. Apache 2.0 weights can be self-hosted.
- Provider
- Alibaba (Qwen)
- Type
- Embedding model
- Released
- Jun 5, 2025
- Context window
- 33K tokens
- Price
- $0.01 per 1M input tokens (hosted)
- Input
- text
- Output
- embedding
- Open weights
- Yes
- License
- Apache 2.0
Best for
- Local & on-device
- Research
- Enterprise
Strengths
- Open weights (Apache 2.0)
- 32K-token inputs
- Multilingual
More from Alibaba (Qwen)
- Qwen3.8 Max — Alibaba (Qwen). Alibaba’s 2.4T-parameter proprietary flagship with video understanding.
- Qwen3.8 2.4T A95B — Alibaba (Qwen). The open-weight variant of Qwen3.8 Max — the largest open model available.
- Qwen3.8 Flash — Alibaba (Qwen). Open multimodal reasoning model for coding, desktop interaction and long video.
- Qwen3.6 35B A3B — Alibaba (Qwen). Tiny-active-parameter open MoE — a local-inference favorite.
- Qwen-Image-3.0-Pro — Alibaba (Qwen). Alibaba’s flagship image model with strong text rendering.
- Qwen-Image-2.1 — Alibaba (Qwen). Highest-ranked open-weight image model in the arena.
- Wan 3.0 — Alibaba (Qwen). #1 in the Artificial Analysis text-to-video arena.
- Qwen-Audio-3.1-TTS-Plus — Alibaba (Qwen). Top-3 voice quality at a quarter of the leader’s price.