qwen
Qwen: Qwen3 Embedding 8B
qwen/qwen3-embedding-8b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3-embedding-8b is the 8B text-to-embeddings variant in Qwen's Qwen3 Embedding series, listed by OpenRouter as text input to embeddings output and documented as built from Qwen/Qwen3-8B-Base. The model card presents it as instruction-aware, multilingual across 100+ languages including programming languages, with configurable embedding dimensions up to 4096. Reported benchmark results are vendor-supplied, and the sources disagree on maximum context length, so treat deployment behavior as workload-dependent rather than proven by this pack alone.[1][2]
Strengths
- Designed for multilingual, cross-lingual, and code retrieval scenarios, with claimed support for 100+ languages.[2]
- Offers flexible output dimensions through MRL-style resizing and accepts task instructions, which the documentation says can improve retrieval results.[2]
- Documented for use with common embedding stacks such as Transformers, Sentence Transformers, vLLM, and Text Embeddings Inference.[2]
Limitations
- It is an embedding model rather than a chat or reasoning model; OpenRouter lists embeddings as the only output and no reasoning capability.[1][2]
- The evidence conflicts on context length: the catalog lists 40960 tokens while the model documentation specifies 32K.[1][2]
- Benchmark results in the pack are vendor-reported, not independently reproduced here; validate latency, memory, and retrieval quality on your own workload.[1][2]
Where to use it
- Semantic search and retrieval-augmented generation where query-side instructions can be tailored to the task.[2]
- Multilingual or cross-lingual document matching and code retrieval across mixed-language corpora.[2]
- Clustering, classification, and bitext mining pipelines that need configurable vector sizes.[2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3 Embedding 8BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3 Embedding 8BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...
Specifications
- Model ID
- qwen/qwen3-embedding-8b
- Creator
- qwen
- Added to OpenRouter
- 28.10.2025
- Context length
- 40,960
- Modality
- text->embeddings
- Input modalities
- text
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.010 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nebiusbf16 | 40,960 | $0.010 | $0 | — | — | 100% |
| DeepInfra | 32,768 | $0.010 | $0 | — | — | 100% |
| SiliconFlowfp8 | 32,768 | $0.040 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.