text-embedding-3-small API

Convert text into vectors for semantic search and similarity workflows. Store vectors in an index with compatible dimensions and use the same model for documents and queries. The batch, input-token and dimension constraints below belong to the current OneAster contract.

openai/text-embedding-3-small · OpenAI · Embedding

Availability and pricing

Published contract · ready

$0.0192 per 1 million input tokens

Prices shown use the public default price group. Your account price and the request quote determine the amount reserved and charged.

Published verification: 2026-10-05T21:32:16.110Z

Pricing revision: rev_008d5c47-4b1d-4a7a-9d75-f1de0aeaf03d

Supported inputs and limits

embeddings

max Input Tokens
2048
max Batch
4
dimensions
{"allowed":[1536],"default":1536}
{
  "kind": "openai_embeddings",
  "modes": [
    "embed"
  ],
  "qualities": [
    "standard"
  ],
  "units": [
    1
  ],
  "aspects": [],
  "resolutions": [],
  "maxReferences": 0,
  "maxInputTokens": 2048,
  "maxBatch": 4,
  "dimensions": {
    "allowed": [
      1536
    ],
    "default": 1536
  }
}

Limitations

  • Draft only until live verification and actual cost reconciliation pass.

API request example

Use your own API key. This is a request body; asynchronous tasks also require checking their status and output.

POST /v1/embeddings
{
  "model": "openai/text-embedding-3-small",
  "input": "Hello"
}
Open API examples

Can I mix vectors from different models?

Vector spaces and dimensions may differ. Use a consistent model and compatible index configuration for documents and queries; do not assume vectors from another model are interchangeable.

Try this model

Sign in and check your available credits before sending a request.

Open Playground Compare models API documentation