OpenAI Embedding 3 Small
by OpenAI
OpenAI's small embedding model.
A strong general-purpose default: 1536 dimensions, multilingual, and cheap enough to re-embed a whole corpus. Dimensions can be shortened for smaller indexes.
More details
OpenAI Embedding 3 Small by OpenAI is a fast-speed text embedding model. A strong general-purpose default: 1536 dimensions, multilingual, and cheap enough to re-embed a whole corpus. Dimensions can be shortened for smaller indexes. It returns 1536-dimension vectors, up to 8,191 tokens per input, batches of 100 inputs per request, multilingual coverage, shortenable output (512, 1024 dimensions).
OpenAI Embedding 3 Small is priced at $0.02 per million input tokens. A million tokens is roughly 750,000 words, so a corpus of a few thousand pages costs $0.02 to embed once. You can embed text with OpenAI Embedding 3 Small on idapt.app alongside 200+ AI models in one workspace.
Pricing
Per 1M input tokens
$0.02
10k texts × 500 tokens
$0.10
Billed on input tokens only - output is vectors
Capabilities
Native dimensions
1536
Max input tokens
8,191
Batch size
100
Tuned for
any
Matryoshka shortening targets
What comes back
A vector of 1536 numbers per input — no text, no file, and nothing to play. A capture records the shape, the norm and a fingerprint so two runs can be compared without shipping the payload:
vector[1536] norm 1.000000 sha256 0f3a91c2… first 8: 0.012, -0.004, …
Illustrative shape, not an embedding of your data.
OpenAI Embedding 3 Small questions
Who makes OpenAI Embedding 3 Small?
OpenAI Embedding 3 Small is made by OpenAI and is served on idapt through the OpenAI API.
How much does OpenAI Embedding 3 Small cost?
$0.02 per million input tokens. Embedding is billed on the text you send in, not on the vector you get back, so a few thousand pages typically cost well under a dollar.
How many dimensions does OpenAI Embedding 3 Small return?
1536 dimensions by default. The output can be shortened to 512, 1024 dimensions when you want a smaller index, at a small cost in retrieval quality.
How much text can OpenAI Embedding 3 Small embed at once?
Each input can be up to 8,191 tokens, and one request can carry up to 100 inputs.
Which languages does OpenAI Embedding 3 Small support?
It is multilingual: text in most major languages can be embedded into the same vector space, so you can compare a query in one language against documents in another.
What is OpenAI Embedding 3 Small best used for?
It is tuned for general-purpose embedding. Use it to build a vector index for semantic search, retrieval-augmented generation, deduplication, clustering or classification.
Embedding a million tokens - roughly 750,000 words - costs about $0.02 on this model.