Embeddings

POST /v1/embeddings generates text embeddings with a chosen model for semantic search, clustering, and retrieval workflows via CometAPI.

POST /v1/embeddings

Python

Single Text

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The food was delicious and the waiter was friendly.",
)

print(response.data[0].embedding[:5])  # First 5 dimensions
print(f"Dimensions: {len(response.data[0].embedding)}")

200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.0021,
        -0.0491,
        0.0209,
        0.0314,
        -0.0453
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}

Overview

The Embeddings API generates vector representations of text that capture semantic meaning. These vectors can be used for semantic search, clustering, classification, anomaly detection, and retrieval-augmented generation (RAG).

CometAPI supports embedding models from multiple providers. Pass one or more text strings and receive back numerical vectors that you can store in a vector database or use directly for similarity calculations.

Available Models

Model	Dimensions	Max Tokens	Best For
text-embedding-3-large	3,072 (adjustable)	8,191	Highest quality embeddings
text-embedding-3-small	1,536 (adjustable)	8,191	Cost-effective, fast
text-embedding-ada-002	1,536 (fixed)	8,191	Legacy compatibility

See the model list for all available embedding models and pricing.

Important Notes

Reducing Dimensions — The text-embedding-3-* models support the dimensions parameter, allowing you to shorten the embedding vector without significant loss of accuracy. This can reduce storage costs by up to 75% while retaining most of the semantic information.

Batch Input — You can embed multiple texts in a single request by passing an array of strings to the input parameter. This is significantly more efficient than making individual requests for each text.

---

Authorizations

Authorization · string · header · required

Bearer token authentication. Use your CometAPI key.

Body

application/json

model · string · required

The embedding model to use. See the Models page for current embedding model IDs.

Example:

"text-embedding-3-small"

input · string string[] integer[][] · required

The text to embed. Can be a single string, an array of strings, or an array of token arrays. Each input must not exceed the model's maximum token limit (8,191 tokens for text-embedding-3-* models).

encoding_format · enum<string> · default: float

The format of the returned embedding vectors. float returns an array of floating-point numbers. base64 returns a base64-encoded string representation, which can reduce response size for large batches.

Available options: float, base64

dimensions · integer

The number of dimensions for the output embedding vector. Only supported by text-embedding-3-* models. Reducing dimensions can lower storage costs while maintaining most of the embedding's utility.

Required range: x >= 1

user · string

A unique identifier for your end-user, which can help monitor and detect abuse.

Response

200 - application/json

A list of embedding vectors for the input text(s).

object · enum<string>

The object type, always list.

Available options: list

Example:

"list"

data · object[]

An array of embedding objects, one per input text. When multiple inputs are provided, results are returned in the same order as the input.

Show child attributes

model · string

The model used to generate the embeddings.

Example:

"text-embedding-3-small"

usage · object

Token usage statistics for this request.

Show child attributes