OpenAI embedding model
text-embedding-3-small
OpenAI Embedding 3 Small
OpenAI's smaller text-embedding-3 model, which OpenAI calls an improved, more performant version of its ada embedding model. it returns 1536-dimension vectors by default and costs less than its sibling text-embedding-3-large.
01
price
per 1M input tokens
embeddings bill input only — there are no output tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
02
what real work costs
| workload | cost |
|---|---|
| index 10,000 help articles ~800 tokens each, 8M tokens | $0.16 |
| index a 1M-line codebase ~10 tokens a line, 10M tokens | $0.20 |
| embed 1M search queries ~20 tokens each, 20M tokens | $0.40 |
at the listed price. re-embedding after a model change costs the same again.
03
specs
- provider
- OpenAI
- max input
- about 8k tokens per text
- dimensions
- 1,536
- storage per 1M vectors
- 6.1 GB at 1,536 dims (float32)
- accepts
- text
- weights
- closed
- model id
text-embedding-3-small
integration notes
- one request takes at most 2,048 inputs and 300,000 tokens summed across them; each input is capped at 8,192 tokens.
- empty strings are rejected as input.
- vectors you shorten by hand must be re-normalized; OpenAI suggests the dimensions parameter instead.
04
benchmarks
as published by the maker; not measured by octomind.
05
when to pick it
pick it if
- you want the hosted embedding model every Octomind plan includes, Free too
- you want embeddings without loading model weights into your machine's memory
- you want shorter vectors via the dimensions parameter to shrink your index
skip it if
- a single input runs past 8,192 tokens, the per-input limit
- you need to embed images; it accepts text only
06
where it sits on price
tied for the lowest price among the 10 embedding models in the catalog.
07
use OpenAI Embedding 3 Small in octomind
octocode, octomind's semantic code search, takes any octohub embedding model by id. one octohub key covers it.
[embedding]
code_model = "octohub:text-embedding-3-small"
text_model = "octohub:text-embedding-3-small"08
compare OpenAI Embedding 3 Small
- text-embedding-3-small vs voyage-4-lite
- text-embedding-3-small vs jina-embeddings-v5-text-nano
- text-embedding-3-small vs text-embedding-3-large
09
similar embeddings
nearest embedding models by price.
- Jina v5 Omni Nano $0.02/M input
- Jina v5 Text Nano $0.02/M input
- Voyage 4 Lite $0.02/M input
- Jina v5 Omni Small $0.05/M input
10
OpenAI Embedding 3 Small faq
how much does text-embedding-3-small cost?
$0.02/M input tokens; embeddings have no output charge. index a 1M-line codebase (~10 tokens a line, 10M tokens) costs about $0.20.
how many dimensions does text-embedding-3-small have?
1,536. at the default size, one million float32 vectors take 6.1 GB.
what is the maximum input length of OpenAI Embedding 3 Small?
about 8k tokens per text (≈ 10 pages of prose or 1,000 lines of code). longer documents need chunking before embedding.
how do i use OpenAI Embedding 3 Small with octocode?
set code_model and text_model to "octohub:text-embedding-3-small" in the [embedding] section of octocode's config.toml, then re-index.
use OpenAI Embedding 3 Small in octomind
use it for semantic code search with octocode, or call it through octohub.