bge-small-en-v1.5

curl --request POST \
  --url https://api.zerogpu.ai/v1/embeddings \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "bge-small-en-v1.5",
  "input": "ZeroGPU runs high-volume inference tasks on small models at the edge."
}
'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.010229,
        0.026804,
        -0.00474,
        -0.025792,
        0.055778,
        0.047825,
        -0.044991,
        0.056061
      ]
    }
  ],
  "model": "bge-small-en-v1.5",
  "usage": {
    "prompt_tokens": 18,
    "total_tokens": 18
  }
}

{}

POST

embeddings

curl --request POST \
  --url https://api.zerogpu.ai/v1/embeddings \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "bge-small-en-v1.5",
  "input": "ZeroGPU runs high-volume inference tasks on small models at the edge."
}
'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.010229,
        0.026804,
        -0.00474,
        -0.025792,
        0.055778,
        0.047825,
        -0.044991,
        0.056061
      ]
    }
  ],
  "model": "bge-small-en-v1.5",
  "usage": {
    "prompt_tokens": 18,
    "total_tokens": 18
  }
}

{}

This model is routable only on /v1/embeddings. A /responses or /chat/completions call with an embedding model returns 400. Send input as a string, or as an array of strings to embed a batch in one request.

BAAI’s BGE-small-en-v1.5 is a retrieval-first English embedding model and one of the strongest performers on the MTEB benchmark for its size. Like all-minilm-l6-v2 it produces 384-dimensional vectors, so it is a drop-in swap in an existing index, but it takes a 512-token window instead of 256 and is tuned specifically for dense retrieval rather than general sentence similarity. At 33.4M parameters it is the one to reach for when the job is ranking passages against a query: RAG retrieval, search over a document corpus, or reranking candidates before they reach a larger model.

Embeddings are priced on input tokens only. There are no output tokens to bill, so a call costs $0.50 per 1M tokens embedded. References: Model card • License • Terms • Privacy

Authorizations

x-api-key

string

header

required

Headers

x-project-id

string

Optional project identifier. Scopes the request to a specific project when provided.

Body

application/json

model

string

default:bge-small-en-v1.5

required

Model identifier (fixed for this playground).

Allowed value: "bge-small-en-v1.5"

Example:

"bge-small-en-v1.5"

input

required

Text to embed. A single string, or an array of strings for one vector per element. Inputs are truncated at 512 tokens.

Required string length: 1 - 131072

Response

Success

An OpenAI-compatible embedding list. Vectors are truncated in this example; each has 384 dimensions.

⌘I

Endpoints

ZeroClick

Batch API

bge-small-en-v1.5

Authorizations

Headers

Body

Response