BAAI

BGE-M3

Name: BGE-M3
Brand: BAAI
Price: 0.0135 USD
Availability: InStock

1024-dimension embeddings across 100+ languages, built for retrieval that has to work in more than English. The 8K window takes a whole page without chunking. Reach for it when the corpus is multilingual and the per-million rate matters.

Modalities

Text → Text

Input

$0.0135 /1M

Output

$0.00 /1M

Cached input

$0.00135 /1M90% off

Context

Speed

fast

Pricing

Pay per token. Cached input is billed at 10% of the input rate.

$0.0135 /1M input$0.00 /1M output

Hobby10 req/day · 2K in / 500 out

~$0.01/mo

Production1,000 req/day · 2K in / 500 out

~$0.81/mo

Scale20,000 req/day · 2K in / 500 out

~$16.20/mo

+ Estimate your workload

Requests / day1,000

Input tokens / request2,000

Output tokens / request500

Cache hit rate30%

Estimated monthly cost

$0.5913

$0.0197 / day on BGE-M3

Same workload on:

BGE Large EN v1.5$0.8100+37%

EmbeddingGemma 300M$0.1620-73%

Estimates use list pricing with cached input billed at the 90%-discount rate. Actual bills depend on real token counts — every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

Spec	BGE-M3	BGE Large EN v1.5	EmbeddingGemma 300M
Input /1M	$0.0135	$0.0135	$0.0027
Output /1M	$0.00	$0.00	$0.00
Context	8K	1K	2K
Tools	Yes	Yes	Yes
Reasoning	No	No	No
Speed	fast	fast	fast

Quick start

Up and running in under two minutes.

1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit, no card required.
Get API key →

Make your first request

Drop in your key and send a chat completion — fully OpenAI-compatible.

curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-m3",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'

Stream responses

Add "stream": true to receive tokens as they arrive.

curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-m3",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of BGE-M3?

BGE-M3 has a 8K-token context window — roughly 12 pages of text in a single request.

How much does the BGE-M3 API cost?

$0.0135 per 1M input tokens and $0.00 per 1M output tokens, with cached input at $0.00135/1M — a 90% discount on repeated prompt prefixes. No subscription; you pay only for what you use.

Does BGE-M3 support function calling?

Yes — BGE-M3 supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

How do I use BGE-M3?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to bge-m3. Signing up is free and includes $0.50 of credit — no card required.

Start with $0.50 free credit — no card required.Create account →

More models by BAAI

Model	Context	Input	Output
BGE Large EN v1.5	1K	$0.0135	$0.00