BAAI Models on XALEN

Beijing Academy of AI. Open embedding and reranking models.

Founded: 2018 · HQ: Beijing, China · 2 models available

Available Models

BGE Large v1.5

Embedding

Cost-effective embeddings with strong multilingual support.

Params: 326M Context: 512 Input: $0.001 Output: N/A Latency: ~15ms

BGE Reranker v2

Reranking

Cross-encoder reranking for improving retrieval precision.

Params: 568M Context: 8K Input: $0.003 Output: N/A Latency: ~30ms

Quick Start

import XALEN from 'xalen-sdk';

const client = new XALEN({ apiKey: 'xln_test_YOUR_KEY' });

const response = await client.chat.completions.create({
  model: 'bge-large-v1-5',
  messages: [{ role: 'user', content: 'Hello!' }]
});

Start Using BAAI Models

All models available through a single API. No separate accounts needed.

Get API Key

Last updated: 2026-05-21.