bge m3
unofficialembedding
bge m3 specifications
| Context window | 60K |
|---|---|
| Max output tokens | — |
| Release date | — |
| Input | Text |
| Output | Vector |
bge m3 pricing in rubles
You pay for what you use, per token and per unit. The final request cost is returned in the API response.
| Type | Price |
|---|---|
| Input tokens | 1,56 ₽ per 1M tokens |
Prices are in rubles and may change with exchange rates.
What bge m3 can do
- Streaming responses
bge m3 API: connection and code examples
The service exposes a single OpenAI-compatible API. Set our base_url and the key from your dashboard.
OpenAI Python SDK
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.neuralbridge.ru/v1")
result = client.embeddings.create(model="baai/bge-m3-08130", input="Текст для векторизации")
print(len(result.data[0].embedding))cURL
curl https://api.neuralbridge.ru/v1/embeddings \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "baai/bge-m3-08130", "input": "Текст для векторизации"}'API endpoints
POST /v1/embeddingsprimary | Embeddings Vector‑embedding van tekst voor zoeken, clustering en nabijheidsbeoordeling. |
Supported request parameters
| Parameter | Default | Allowed values | Description |
|---|---|---|---|
dimensions | — | — | Dimensie van de embedding‑vector: een kortere vector neemt minder ruimte in en zoekt sneller, maar geeft een minder nauwkeurige overeenkomst. |
encoding_format | float | — | Hoe de vector te leveren: als getallenarray of als base64‑string. |