Voyage AI embedding model
voyage-code-4
Voyage Code 4
Voyage Code 4 is Voyage AI's code-retrieval embedding model, trained so natural-language queries such as bug reports find the right code for coding agents. it succeeds voyage-code-3 at a third lower price.
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 | $0.96 |
| index a 1M-line codebase ~10 tokens a line, 10M tokens | $1.20 |
| embed 1M search queries ~20 tokens each, 20M tokens | $2.40 |
at the listed price. re-embedding after a model change costs the same again.
03
specs
- provider
- Voyage AI
- max input
- about 32k tokens per text
- dimensions
- 1,024 by default; also 256, 512 and 2,048
- storage per 1M vectors
- 4.1 GB at 1,024 dims · 2 GB at 512 dims · 1 GB at 256 dims (float32)
- accepts
- text, code
- weights
- closed
- released
- August 13, 2026
- model id
voyage-code-4
integration notes
- context length is 32,000 tokens; over-length inputs are silently truncated unless truncation is set to false.
- a single request accepts at most 1,000 texts in its input list.
- set input_type to query or document so Voyage prepends its retrieval prompt; None embeds the raw text.
04
when to pick it
pick it if
- you index source code for coding agents or natural-language code search
- you want Voyage's reported 27.54% gain over voyage-code-3 on agentic retrieval
- you need 256-2048 Matryoshka dimensions to trade index size for accuracy
skip it if
- your corpus is general prose; voyage-4-lite costs a sixth as much
- you need open weights to embed code on your own hardware
05
where it sits on price
8th cheapest of the 10 embedding models in the catalog.
06
use Voyage Code 4 in octomind
octocode, octomind's semantic code search, takes any octohub embedding model by id. one octohub key covers it.
[embedding]
code_model = "octohub:voyage-code-4"
text_model = "octohub:voyage-code-4"07
compare Voyage Code 4
08
similar embeddings
nearest embedding models by price.
- Voyage 4 Large $0.12/M input
- OpenAI Embedding 3 Large $0.13/M input
- Voyage 4 $0.06/M input
- Jina v5 Omni Small $0.05/M input
09
Voyage Code 4 faq
how much does voyage-code-4 cost?
$0.12/M input tokens; embeddings have no output charge. index a 1M-line codebase (~10 tokens a line, 10M tokens) costs about $1.20.
how many dimensions does voyage-code-4 have?
1,024 by default; also 256, 512 and 2,048. at the default size, one million float32 vectors take 4.1 GB.
what is the maximum input length of Voyage Code 4?
about 32k tokens per text (≈ 50 pages of prose or 3,000 lines of code). longer documents need chunking before embedding.
how do i use Voyage Code 4 with octocode?
set code_model and text_model to "octohub:voyage-code-4" in the [embedding] section of octocode's config.toml, then re-index.
use Voyage Code 4 in octomind
use it for semantic code search with octocode, or call it through octohub.