● BAAI · embedding

BGE-M3

SAMPLE: Multilingual embedding model for search and retrieval.

Get API key All models

Input / 1M tokens$0.01

Context8K

Example: 1M input tokens = $0.01

Call BGE-M3

OpenAI-compatible. Use any OpenAI SDK with the Keyra base URL and your key.

curl

curl https://api.keyra.example/v1/embeddings \
  -H "Authorization: Bearer $KEYRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bge-m3", "input": "Hello, world"}'

Python · openai SDK

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.keyra.example/v1", api_key=os.environ["KEYRA_API_KEY"])

result = client.embeddings.create(model="bge-m3", input="Hello, world")
print(len(result.data[0].embedding))

Related models

Model	Creator	Type	Context	Input / 1M	Output / 1M
Qwen3 Embedding 8B	Qwen	embedding	32K	$0.02	—