OpenAI embedding model
text-embedding-3-large
OpenAI Embedding 3 Large
text-embedding-3-large is the larger of OpenAI's two third-generation text embedding models, returning 3072-dimension vectors by default. it sits above text-embedding-3-small, which costs less per token and returns 1536-dimension vectors.
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 | $1.04 |
| index a 1M-line codebase ~10 tokens a line, 10M tokens | $1.30 |
| embed 1M search queries ~20 tokens each, 20M tokens | $2.60 |
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
- 3,072
- storage per 1M vectors
- 12.3 GB at 3,072 dims (float32)
- accepts
- text
- multilingual
- yes
- weights
- closed
- released
- January 25, 2024
- model id
text-embedding-3-large
integration notes
- each input must not exceed 8,192 tokens, and an empty string is rejected.
- one request is capped at 300,000 tokens summed across all inputs.
04
benchmarks
as published by the maker; not measured by octomind.
| benchmark | score |
|---|---|
| MTEBsource | 64.6% |
05
when to pick it
pick it if
- retrieval quality matters more than cost per token
- you want shorter vectors via the dimensions parameter, for example 256
- you embed non-English as well as English text
skip it if
- text-embedding-3-small is accurate enough at a lower price
- you need to embed images; it accepts text only
06
where it sits on price
10th cheapest of the 10 embedding models in the catalog.
07
use OpenAI Embedding 3 Large 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-large"
text_model = "octohub:text-embedding-3-large"08
compare OpenAI Embedding 3 Large
09
similar embeddings
nearest embedding models by price.
- Voyage 4 Large $0.12/M input
- Voyage Code 4 $0.12/M input
- Voyage 4 $0.06/M input
- Jina v5 Omni Small $0.05/M input
10
OpenAI Embedding 3 Large faq
how much does text-embedding-3-large cost?
$0.13/M input tokens; embeddings have no output charge. index a 1M-line codebase (~10 tokens a line, 10M tokens) costs about $1.30.
how many dimensions does text-embedding-3-large have?
3,072. at the default size, one million float32 vectors take 12.3 GB.
what is the maximum input length of OpenAI Embedding 3 Large?
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 Large with octocode?
set code_model and text_model to "octohub:text-embedding-3-large" in the [embedding] section of octocode's config.toml, then re-index.
use OpenAI Embedding 3 Large in octomind
use it for semantic code search with octocode, or call it through octohub.