EmbeddingMultilingual
BGE-M3
Embedding generation for RAG and semantic search.
bge-m3Designed for your workflow
From input to useful output.
InputText
ModelBGE-M3
OutputEmbedding vectors
Explore these use cases
- 01Multilingual semantic search
- 02RAG document indexing
- 03Content similarity
Model capabilities
Published catalog- Context window
- 8K
- Maximum output
- Vector
- Serving region
- Thailand · TH
- Streaming
- Not listed
- Tool use
- Not listed
- Structured output
- Not listed
- Reasoning
- Not listed
Catalog specifications describe the model configuration. Check service status before sending requests.
Build with this model
Generate embeddings for storage in your own search or vector system. Pair with a reranker when your retrieval workflow needs a second ranking stage.
- API base URL
https://b300.powerchampion.ai/v1- Endpoint
- POST
/v1/embeddings - Authentication
Authorization: Bearer YOUR_API_KEY