Gemini Embedding 001
by Google
Google's retrieval-tuned embedding model.
Gemini Embedding 001 handles search, classification and clustering across languages, with task-instruction prefixes and shortened output dimensions.
More details
Gemini Embedding 001 by Google is a standard-speed text embedding model. Gemini Embedding 001 handles search, classification and clustering across languages, with task-instruction prefixes and shortened output dimensions. It returns 3072-dimension vectors, up to 2,048 tokens per input, batches of 100 inputs per request, multilingual coverage, shortenable output (768, 1536 dimensions), instruction prefixes for asymmetric retrieval.
Gemini Embedding 001 is priced at $0.15 per million input tokens. A million tokens is roughly 750,000 words, so a corpus of a few thousand pages costs $0.15 to embed once. You can embed text with Gemini Embedding 001 on idapt.app alongside 200+ AI models in one workspace.
Pricing
Per 1M input tokens
$0.15
10k texts × 500 tokens
$0.75
Billed on input tokens only - output is vectors
Capabilities
Native dimensions
3072
Max input tokens
2,048
Batch size
100
Tuned for
search
Matryoshka shortening targets
What comes back
A vector of 3072 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[3072] norm 1.000000 sha256 0f3a91c2… first 8: 0.012, -0.004, …
Illustrative shape, not an embedding of your data.
Gemini Embedding 001 questions
Who makes Gemini Embedding 001?
Gemini Embedding 001 is made by Google and is served on idapt through the Google API.
How much does Gemini Embedding 001 cost?
$0.15 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 Gemini Embedding 001 return?
3072 dimensions by default. The output can be shortened to 768, 1536 dimensions when you want a smaller index, at a small cost in retrieval quality.
How much text can Gemini Embedding 001 embed at once?
Each input can be up to 2,048 tokens, and one request can carry up to 100 inputs.
Which languages does Gemini Embedding 001 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 Gemini Embedding 001 best used for?
It is tuned for search and retrieval. Use it to build a vector index for semantic search, retrieval-augmented generation, deduplication, clustering or classification.
Does Gemini Embedding 001 take instructions?
Yes. You can prefix the text with a short task instruction (for example, a query intent), which improves asymmetric retrieval where the query and the document are not shaped alike.
Embedding a million tokens - roughly 750,000 words - costs about $0.15 on this model.