qwen
Qwen3 Reranker 8B
qwen/qwen3-reranker-8b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3-reranker-8b is an 8B-parameter text-ranking model from Alibaba Cloud's Qwen3 family, built from Qwen/Qwen3-8B-Base and distributed under Apache-2.0. The model card describes it as scoring query-document relevance for retrieval and RAG, with support for more than 100 languages and customizable instructions. Vendor-reported evaluation covers multilingual and code retrieval; OpenRouter lists text input and reranking output. Treat the listed context window cautiously because the catalog and model card disagree.[1][2]
Strengths
- Purpose-built for query-document relevance scoring in retrieval and RAG pipelines.[1][2]
- Model documentation reports support for more than 100 languages, including programming languages, and customizable reranking instructions.[2]
- Vendor-run evaluations cover English, Chinese, multilingual, code-retrieval, and instruction-following retrieval tasks.[2]
Limitations
- OpenRouter lists a 40,960-token context while the model card specifies 32k; verify the deployed limit.[1][2]
- Hardware requirements, latency, and throughput are not provided in the supplied evidence.[2]
- Evidence is limited to a catalog listing and vendor materials, so ranking quality should be validated on the target workload.[1][2]
Where to use it
- Consider for second-stage reranking of retrieved passages in RAG systems.[1][2]
- Potentially useful for multilingual or cross-lingual search where its language coverage matches the corpus.[2]
- Candidate for code or technical-document retrieval ranking, subject to custom instructions and task-specific evaluation.[2]
Sources
- [1] OpenRouter catalog · Qwen3 Reranker 8BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen3 Reranker 8BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG...
Specifications
- Model ID
- qwen/qwen3-reranker-8b
- Creator
- qwen
- Added to OpenRouter
- 13.08.2026
- Context length
- 40,960
- Modality
- text->rerank
- Input modalities
- text
- Output modalities
- rerank
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- 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 | — |
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) |
|---|---|---|---|---|---|---|
| PrimeIntellectbf16 | 32,768 | — | — | — | — | 100% |
| Fireworks | 40,960 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.