BGE-M3

BGE-M3 is available after commercial review or workspace setup.

Model detailAccess reviewEncoder Transformer

Params

568M

Context

Max Output

N/A

License

MIT

API Surface

/v1/embeddings

Access

Access review

Why pick it

Access is enabled only after workspace setup or commercial review.
Pricing appears only when verified by the live service catalog.

Pricing

TierPublicCachedNote

Realtime$0.006 / $0.000$0.002Current published price

Batch$0.006 / $0.000$0.002Published batch rates appear here when available

Current pricing synced from the BatchIn catalog.

Quick start

This model is not yet open for public testing. Contact the team for the right access path.

Contact team Open pricing

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.batchin.tech/v1",
    api_key="BATCHIN_API_KEY"
)

resp = client.embeddings.create(
    model="bge-m3",
    input=["BatchIn inference platform"]
)

print(resp.data[0].embedding[:8])

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.batchin.tech/v1",
  apiKey: process.env.BATCHIN_API_KEY,
});

const resp = await client.embeddings.create({
  model: "bge-m3",
  input: ["BatchIn inference platform"],
});

console.log(resp.data[0]?.embedding?.slice(0, 8));

cURL

curl https://api.batchin.tech/v1/embeddings \  -H "Authorization: Bearer ***" \  -H "Content-Type: application/json" \  -d '{
    "model": "bge-m3",
    "input": ["BatchIn inference platform"]
  }'

Specs

Architecture

Encoder Transformer

Vendor

BAAI

Context window

Max output

N/A

Best for

baai

request-access

Related models

Back to model center