vLLM Embedding API (1.0.0)

Download OpenAPI specification:Download

OpenAI-compatible embedding service powered by vLLM

Embeddings

Create Embeddings

Generate embeddings for the provided input texts (OpenAI-compatible).

Authorizations:

HTTPBearer

Request Body schema: application/json

required	Input (string) or Array of Input (strings) (Input)
model required	string (Model)
encoding_format	string (Encoding Format) Default: "float"

Responses

Request samples

Payload

Content type

application/json

{"input": "string",
"model": "string",
"encoding_format": "float"
}

Response samples

200
422

Content type

application/json

{"object": "list",
"data": [{"object": "embedding",
"embedding": [0
],
"index": 0
}
],
"model": "string",
"usage": {"prompt_tokens": 0,
"total_tokens": 0
}
}

Models

List Models

Return the list of available models (OpenAI-compatible).

Authorizations:

HTTPBearer

Responses

Response samples

200

Content type

application/json

{"object": "list",
"data": [{"id": "string",
"object": "model",
"owned_by": "local"
}
]
}

Health

Responses

Response samples

200

Content type

application/json

{ }