Qwen·Qwen

Qwen3 Embedding 8b

qwen/qwen3-embedding-8b

2 providers · cheapest €0.00/M via Scaleway

Try in Playground Copy code Docs

operationalZDRembeddings

01·01

Overview

Modell-Beschreibung und Capability-Matrix.

About this model

Keine Beschreibung verfügbar. Modelle werden über das Gateway-Catalog gepflegt und automatisch synchronisiert.

Capabilities matrix

streaming—

tools—

json—

vision—

reasoning—

embedding—

02·02

Providers

2 EU-Provider mit Pricing, Throughput, Latency und Uptime — sortierbar. Pin-Button kopiert den X-CleverRouter-Provider-Header.

	Provider Model ID	Context	ZDR						Pin
Scaleway	qwen3-embedding-8b	fr-par-1	ZDR	€0.08	€0.00	—	—	100.00%
Tensorix	qwen/qwen3-embedding-8b	ie-dub-1	ZDR	€0.08	€0.00	—	—	98.90%

Pin kopiert X-CleverRouter-Provider-Header. Setze ihn an deinen Request, um Routing zu fixieren.

03·03

Code samples

Drop-in OpenAI-kompatibel — drehe an System-Prompt, Temperatur, Max-Tokens und Streaming, die Snippets aktualisieren sich live.

Input text

use-qwen3-embedding-8b.ts

curl https://cleverouter.eu/v1/embeddings \
  -H "Authorization: Bearer $CLEVERROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen/qwen3-embedding-8b",
  "input": "best vector database for production"
}'

04·04

Performance

Throughput, TTFT, E2E-Latency und Tool-Error-Rate — pro Provider, p50 über 24h.

No performance data for this model yet. Once the first requests roll through, p50/p95 latency, throughput and error rate per provider will appear here.

Scaleway

fr-par-1

Throughput

—tok/s

p50 · 24h

TTFT

—ms

p50 · 24h

E2E Latency

—s

p50 · 24h

Tool Err Rate

—%

last 7d

Tensorix

ie-dub-1

Throughput

—tok/s

p50 · 24h

TTFT

—ms

p50 · 24h

E2E Latency

—s

p50 · 24h

Tool Err Rate

—%

last 7d

Source · Aggregiert aus der requests Tabelle, letzte 24 h. p50/p95 via Postgres-Native PERCENTILE_CONT.

05·05

Uptime

30-Tage-Heatmap pro Provider, aggregierte Verfügbarkeit und Incident-Historie.

Aggregated uptime

99.45%

Last 30 days · all providers combined

≥ 99 %95–99 %< 95 %no data

Scaleway

fr-par-1ZDR

100.00%

last 30 days

Tensorix

ie-dub-1ZDR

98.90%

last 30 days

Recent incidents · last 30 days

Keine Incidents in den letzten 30 Tagen.

06·06

Apps & use cases

What you can typically build with Qwen embedding models — ready-made snippets to get you started.

RAG-Pipelines

Dokumente einbetten, in pgvector / Pinecone ablegen und kontextuelle Antworten an dein Chat-Modell durchreichen.

const { data } = await client.embeddings.create({
  model: 'qwen/qwen3-embedding-8b',
  input: chunks,
});
await db.insert(vectors).values(
  chunks.map((c, i) => ({ chunk: c, embedding: data[i].embedding }))
);

Semantic search

Cosine-Similarity gegen die Wissensbasis — semantische Suche für Produkt-Catalogs, Helpdesk und interne Wikis.

const q = await client.embeddings.create({
  model: 'qwen/qwen3-embedding-8b',
  input: [userQuery],
});
const hits = await db.execute(sql`
  SELECT * FROM vectors
  ORDER BY embedding <=> ${q.data[0].embedding}::vector
  LIMIT 10`);

Clustering & dedup

Themen-Clustering von Tickets, Reviews oder News — Centroids berechnen, Outlier flaggen, Duplikate erkennen.

const embeds = await client.embeddings.create({
  model: 'qwen/qwen3-embedding-8b',
  input: docs,
});
// k-means / HDBSCAN auf embeds.data[].embedding