Skip to main content

openai/text-embedding-3-small/embedding

text-embedding-3-small turns notes and document passages into compact search vectors, with 1,536 dimensions by default and optional shorter output.

From $0.000004/1,000 tokens80% below the publisher's list price

Workbench

Input

Embedding
Reduce 3-small output with dimensions from 1 to 1,536; use the same length for indexed passages and queries. no lower than 1 · no higher than 1536
For 3-small, embed each passage separately; send a string, strings, token IDs or batches of token ID arrays.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result
{"data":[{"embedding":[0.52685546875,0.419189453125,0.6533203125,-0.0018758773803710938,-0.25048828125,-0.0029315948486328125,0.2252197265625,-0.07879638671875],"index":0},{"embedding":[-0.0767822265625,0.150146484375,0.52099609375,0.15771484375,-0.184814453125,0.0173492431640625,-0.5791015625,-0.55224609375],"index":1}],"inputTokens":12}

Missing the model you need?

Start a new notes index with 3-small, then compare retrieval quality at 256 dimensions before choosing the storage size.

Key numbers

Dimensions
1536

Token budget

Input window
300,000
tokens in one request

Before you spend

Embedding

text-embedding-3-small accepts up to 128 inputs per platform request, each within 8,192 tokens, with at most 300,000 tokens in total; token ID arrays are capped at 2,048 entries.

What it does

Adjustable compact vectors

The adjustable output of 3-small lets a notes application compare a compact 256-dimensional index with the default representation. A smaller vector needs less space, but that tradeoff should be checked against the questions people actually ask. Keep the chosen length consistent across the documents and queries belonging to a collection.

Separate vectors for each passage

Batch submission with 3-small preserves a separate vector for each supplied passage. The result index connects each vector to its original input, so your application can attach its own document ID, source location and access rules. This endpoint accepts up to 128 inputs per request; billing follows measured input tokens across the batch.

Where it fits

  • Search a personal notebook

    For a personal notebook using 3-small, store short passages with their note IDs and search for related material even when the query uses different wording. Return the original passage alongside each match so readers can inspect its meaning and date.

  • Retrieve approved support articles

    For a support library using 3-small, compare a customer question with approved help articles and pass the selected sources to a separate writing model. A close vector match is a retrieval signal; your application still decides which articles the customer is allowed to see.

Model reference

text-embedding-3-small API reference

text-embedding-3-small API specifications

Dimensions
1536

How to call the text-embedding-3-small API

  1. Prompt guide & Pro tips

    Prepare 3-small input by dividing long documents at useful section boundaries and retaining a small amount of overlapping context where a passage would otherwise become ambiguous. Send the actual text to represent, without an instruction to invent an answer. Empty strings are rejected, each item must fit within 8,192 tokens, and the request total must stay within 300,000 tokens. Pre-tokenized arrays have a 2,048-entry limit. Before committing a 3-small index to production, evaluate known queries against the default dimensions and at least one shorter setting. Save the model ID, dimensions and chunking version with the index; changing these choices requires rebuilding the affected vectors. Apply account and project access filters when selecting candidates, and remove indexed entries when their source note is deleted.

text-embedding-3-small API questions

All text-embedding models3