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

$0.13/M

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

workloadcost
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.

benchmarkscore
MTEBsource64.6%

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

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.

octocode config.toml
[embedding]
code_model = "octohub:text-embedding-3-large"
text_model = "octohub:text-embedding-3-large"

08

compare OpenAI Embedding 3 Large

all model comparisons →

09

similar embeddings

nearest embedding models by price.

view all models →

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.