BGE-EN-ICL API

BGE-EN-ICL is an embedding model by BAAI, available on the Venice API as text-embedding-bge-en-icl. It runs privately, with zero data retention.

BGE-EN-ICL API pricing

Model ID	Variant	Privacy	Price
`text-embedding-bge-en-icl`	Standard	Private	$0.01 per 1M tokens

BGE-EN-ICL specifications

Spec	Value
Provider	BAAI
Released	Apr 17, 2026
Privacy	Private
Open weights	Yes
Dimensions	4,096
Max input	8K tokens

How to use the BGE-EN-ICL API

Send requests to POST https://api.venice.ai/api/v1/embeddings with "model": "text-embedding-bge-en-icl" and your API key.

curl https://api.venice.ai/api/v1/embeddings \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-bge-en-icl",
    "input": "Private AI for everyone."
  }'

BGE-EN-ICL API FAQ

How much does the BGE-EN-ICL API cost?

$0.013 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.

What is the BGE-EN-ICL model ID?

Use text-embedding-bge-en-icl as the model parameter.

Is the BGE-EN-ICL API private?

BGE-EN-ICL is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

How many dimensions do BGE-EN-ICL embeddings have?

4,096 dimensions, with up to 8K input tokens per item.

Which endpoint does the BGE-EN-ICL API use?

Call POST /embeddings.

Related models

Multilingual E5 Large Instruct API: $0.01 per 1M tokens
Nemotron Embed VL 1B v2 API: $0.01 per 1M tokens
Qwen3 Embedding 0.6B API: $0.01 per 1M tokens
Qwen3 Embedding 8B API: $0.01 per 1M tokens

Explore

By modality