Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector
Paired with bge-m3 for two-stage retrieval: recall with embeddings, precision with this reranker.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Bge-Base-EN-V1.5
client.chat.completions.create(
model="baai/bge-base-en-v1.5",
messages=[{"role":"user","content":"hello"}],
)
# BGE Reranker Base
client.chat.completions.create(
model="baai/bge-reranker-base",
messages=[{"role":"user","content":"hello"}],
)