$5 free credits when you sign up NEW Music generation - Ace-Step 1.5 Turbo NEW Wan 2.2 Animate now available
Models Pricing Enterprise Docs
Text to Image Text to Speech Image to Text Image to Image Video to Text Image to Video Text to Music
Sign in Get Started
Text-to-Embedding

BGE M3

Free Playground & API · $5 to Start

1024-dimensional vectors. Up to 8192 tokens per input, 245K total. Multilingual support. Ideal for RAG, semantic search, and similarity matching.

Get $5 credits
No subscription
No credit card required
HuggingFace

Capabilities

Model ID: Bge_M3_FP16

What you can do with BGE M3.

Text-to-Embedding

Convert text into vector embeddings for semantic search, recommendations, and RAG applications.

Technical Specifications

Max Input

8,192 tokens

Max Total

245,760 tokens

How to Use in deAPI

Integrate BGE M3 into your app with a single API call.

POST https://api.deapi.ai/api/v1/client/txt2embedding 
curl -X 'POST' \
  'https://api.deapi.ai/api/v1/client/txt2embedding' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{
    "model": "Bge_M3_FP16",
    "texts": [
        "Hello world",
        "Semantic search example"
    ]
}'
{
    "model": "Bge_M3_FP16",
    "texts": [
        "Hello world",
        "Semantic search example"
    ]
}

Tip: The API returns a request_id. Use webhooks (recommended) or poll GET /request-status/{'{'}request_id{'}'} for results.

Need an API key?

Sign up for free and get $5 in credits to start.

Get $5 credits
Get started with BGE M3
1

Sign Up & Get $5 Free

No credit card required

 2

Open Playground or API

Call the REST API directly

3

Generate & Ship

Use in your app, product, or workflow

Frequently Asked Questions

1024-dimensional vectors. Up to 8192 tokens per input, 245K total. Multilingual support. Ideal for RAG, semantic search, and similarity matching.
BGE M3 produces 1024-dimensional vectors. It handles up to 8,192 tokens per input and 245,760 tokens total per request. It supports multiple languages natively.
BGE M3 embeddings are used for semantic search (finding similar content by meaning), RAG (Retrieval-Augmented Generation) to give LLMs context, document clustering, recommendation systems, and duplicate detection.
Sign up for a free deAPI account at https://deapi.ai/register and get $5 in free credits — no credit card required. Then open the playground, select BGE M3, and generate your first result in seconds.
deAPI is pay-per-use with no subscriptions or monthly fees. Check the pricing page at https://deapi.ai/pricing for current per-generation rates.
Yes. BGE M3 is available via the deAPI REST API. Submit a request, receive a request ID, and poll for the result. See the API documentation at https://docs.deapi.ai for code examples in Python, Node.js, and cURL.

Try BGE M3 for Free

Get $5 in free credits and start generating with BGE M3.

Get $5 credits
No subscription
No credit card required
Pay only for what you use