Embeddings

OpenAI-compatible embedding requests against open-weight embedding models on the /oss lane.

posthttps://api.opengateway.one/oss/v1/embeddings

Request

curl

curl https://api.opengateway.one/oss/v1/embeddings \
  -H "Authorization: Bearer $OPENGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "intfloat/multilingual-e5-large",
    "input": "OpenGateway routes open models at the edge."
  }'

Response

json

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0123, -0.0456, "..."] }
  ],
  "model": "intfloat/multilingual-e5-large",
  "usage": { "prompt_tokens": 9, "total_tokens": 9 }
}

Embedding models

Model	Dim	Best for
`intfloat/multilingual-e5-large`	1024	Default multilingual retrieval
`thenlper/gte-large`	1024	General-purpose embeddings
`ibm-granite/granite-embedding-97m-multilingual-r2`	—	Compact, low-cost multilingual

Batch input

Pass an array to input to embed many strings in one call:

python · openai sdk

from openai import OpenAI

client = OpenAI(base_url="https://api.opengateway.one/oss/v1", api_key="YOUR_KEY")
resp = client.embeddings.create(
    model="intfloat/multilingual-e5-large",
    input=["first document", "second document"],
)
print(len(resp.data))