BGE-M3
BAAI's versatile embedding model supporting dense, sparse, and multi-vector retrieval. Open-source and highly effective.
Vector output (1536 dimensions):
Pricing
API Integration
Use our OpenAI-compatible API to integrate BGE-M3 into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
const vectors = await rw.run("bge-m3", "Hello world", { type: "embed" });
console.log(vectors[0].length); // embedding dimensions
// Or use the embed() method for full control
const res = await rw.embed("bge-m3", ["Hello", "World"]);
for (const item of res.data) {
console.log(item.embedding.length);
}Free credits on sign-up
Related Models
View all EmbeddingsText Embedding 3 Large
OpenAI's most powerful embedding model. 3072 dimensions for maximum accuracy.
Cohere Embed v3
Cohere's multilingual embedding model. Supports 100+ languages with separate search and classification modes.
Jina Embeddings v3
Jina AI's latest embedding model with task-specific adapters. Supports flexible dimensions and multiple retrieval tasks.
Text Embedding 3 Small
OpenAI's compact embedding model. 1536 dimensions, great for semantic search and RAG.
Start using BGE-M3 today
Get started with free credits. No credit card required. Access BGE-M3 and 100+ other models through a single API.