Models / Embeddings / BAAI

BGE-EN-ICL API pricing

$0.03125 per million input tokens, on /v1/embeddings.

bge-en-iclEmbeddings/v1/embeddings

Price · per million input tokens, USD

Get a key
TokensUplinkSwitch
One million input tokens$0.03125
100 million input tokens$3.13
One billion input tokens$31.25
Prices read from the live catalog on 2026-11-04; the page follows the catalog.

BGE-EN-ICL specs

Input limit
8,192 tokens
Developer
BAAI

BGE-EN-ICL API request

curl
curl https://api.uplinkswitch.com/v1/embeddings \
  -H "Authorization: Bearer $UPLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bge-en-icl", "input": ["How do I rotate an API key?", "Billing questions"]}'
Python
from openai import OpenAI

client = OpenAI(base_url="https://api.uplinkswitch.com/v1", api_key="sk-uplink-live-...")

res = client.embeddings.create(model="bge-en-icl", input=["How do I rotate an API key?"])
print(len(res.data[0].embedding))

BGE-EN-ICL questions

$0.03125 per million input tokens, from the live catalog. It is billed per input token; the answer’s usage gives the count. An embedding has no output tokens.

/v1/embeddings on https://api.uplinkswitch.com, in OpenAI's request format, with the same sk-uplink- key and prepaid balance as every chat model. Send "bge-en-icl" as the model.

Yes. Point the SDK's base URL at https://api.uplinkswitch.com/v1 and use your key.

BGE Base EN v1.5 ($0.1665 per million input tokens), BGE-M3 ($0.0295 per million input tokens), BGE Small EN v1.5 ($0.0505 per million input tokens), Gemini Embedding 001 ($0.15 per million input tokens), Multilingual E5 Large Instruct ($0.03125 per million input tokens), Qwen3 Embedding 0.6B ($0.0295 per million input tokens), Qwen3 Embedding 8B ($0.03125 per million input tokens), Text Embedding 3 Large ($0.13 per million input tokens), Text Embedding 3 Small ($0.027089 per million input tokens), Text Embedding Ada 002 ($0.12 per million input tokens). Every one is on the same key.