All models
Qwen
Qwen3 Embedding 8B
Qwen3's flagship multilingual embeddings
Text
Vector 4096
- Type
- Embeddings
- Context
- 33K tokens
- Russian
- high
- Price
- 0,8 ₽ / 1M tokens
- Vector size
- 4096
- Release date
- June 2025
chat/completions
import OpenAI from "openai"const client = new OpenAI({ baseURL: "https://api.yenisei.ru/v1", apiKey: process.env.YENISEI_API_KEY,})const stream = await client.chat.completions.create({ model: "qwen3-embedding-8b", messages: [{ role: "user", content: "Hi!" }], stream: true,})for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? "")}About the model
Qwen3 Embedding 8B is the flagship embeddings model in the Qwen lineup, focused on search quality. It turns text into vector representations and accurately measures the semantic similarity between a query and documents, which is what semantic search and RAG need. The model handles Russian and many other languages confidently. The resulting vectors work well for clustering, recommendations, deduplication and text classification. Its larger size yields more accurate results, so choose it when search quality matters more than cost.
Strengths
- High search quality
- Search across text in Russian and other languages
- Accurate measurement of semantic similarity
- Vectors for clustering and recommendations
- Suited to RAG and semantic search
- Consistent results on demanding tasks
Where to use it
- Semantic search across documents
- RAG pipelines and question-answering systems
- Clustering and topic grouping
- Recommendation systems
- Deduplication and similarity search
- Vector-based text classification