BGE-M3
Embeddingsbge-m3
BGE-M3 on FlexAI: BAAI Embeddings, MIT license, served via the OpenAI-compatible Token Factory at the live market-tracked rate.
Recommended for
Context
8K tokens
API endpoint
/v1/embeddings
Compatibility
OpenAI
Parameters
568M
License
MIT
Hardware
H100
Quantization
FP16
Estimate your monthly cost
M tokens
10M × $0.009/M input$0.09
Estimated monthly cost$0.09
Estimate only, at the current market-tracked rate. Usage-based; no minimums.
Get an API keyQuick Start
bge-m3
from openai import OpenAI
client = OpenAI(base_url="https://tokens.flex.ai/v1", api_key="your-api-key")
response = client.embeddings.create(
model="bge-m3",
input=["Hello, world", "Embeddings are great for RAG"],
)
# response.data is a list of objects, one per input.
for item in response.data:
print(f"index={item.index} dim={len(item.embedding)}")