Skip to main content

openai/text-embedding-3-large/embedding

text-embedding-3-large represents multilingual documents with 3,072 dimensions by default and supports smaller vectors when storage is constrained.

From $0.000026/1,000 tokens80% below the publisher's list price

Workbench

Input

Embedding
Choose 1–3,072 dimensions for 3-large; a 1,024-dimensional request was verified with a two-passage batch. no lower than 1 · no higher than 3072
For 3-large, provide the passages themselves rather than instructions to answer a question; each batch result retains its input index.
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":[-0.30419921875,-0.42626953125,-0.288330078125,-0.5634765625,0.04010009765625,0.0148773193359375,-0.0760498046875,0.56396484375],"index":0},{"embedding":[-0.296875,-0.2344970703125,-0.12493896484375,-0.1837158203125,-0.27587890625,-0.448974609375,-0.44287109375,0.57763671875],"index":1}],"inputTokens":12}

Missing the model you need?

Evaluate 3-large on questions in the languages your collection uses; its adjustable output can fit an existing 1,024-dimensional index after re-embedding.

Key numbers

Dimensions
3072

Token budget

Input window
300,000
tokens in one request

Before you spend

Embedding

text-embedding-3-large 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

Multilingual semantic representations

The multilingual focus of 3-large is useful when questions and source documents do not use the same language. Evaluate that behavior with examples from your own corpus rather than assuming every translation or specialist term will retrieve equally well. The generated vectors describe semantic relationships; they do not contain a citation, a confidence guarantee or a final answer.

Choose 3,072 or a shorter vector

The dimensions option in 3-large can reduce the default representation, including to 1,024 dimensions. A two-passage request at that length and a separate default-length request were verified through the integration. Output length is a storage and retrieval-quality decision, while the measured input token count remains the billing basis for a completed batch.

Where it fits

  • Multilingual product knowledge

    For a multilingual product knowledge base with 3-large, retrieve source passages for questions written in the customer's language. Keep language, product edition and document revision as separate metadata so an apparently relevant older manual does not displace the current instructions.

  • Evidence retrieval for research

    For a research collection indexed with 3-large, rank passages from technical documents and supply their original sources to a downstream analysis model. Preserve document boundaries and reference IDs so the final explanation can be checked against the retrieved evidence.

Model reference

text-embedding-3-large API reference

text-embedding-3-large API specifications

Dimensions
3072

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

  1. Prompt guide & Pro tips

    When testing 3-large, build a small set of answerable questions in the languages your users actually use, together with the passages that should be found. Include abbreviations, near-duplicate documents and questions with no suitable source. Compare retrieval results at 3,072 and 1,024 dimensions before choosing the index layout; using the same vector length alone does not make representations from different models interchangeable. Send 3-large one passage or a homogeneous batch of strings or token arrays. The platform accepts up to 128 items, each within 8,192 tokens, and no more than 300,000 tokens across the request; token arrays are limited to 2,048 entries. Check the returned indexes before storing the vectors, use the same model and dimensions for queries, and rebuild a document's vector after its content changes.

text-embedding-3-large API questions

All text-embedding models3