model comparison

vs

text-embedding-3-small vs voyage-4-lite

compared on price, indexing cost, vector size and input limits.

the short answer

  • OpenAI Embedding 3 Small and Voyage 4 Lite cost the same, $0.02/M tokens.
  • Voyage 4 Lite takes longer inputs (32k tokens against 8k tokens), so it needs less chunking.
  • Voyage 4 Lite returns smaller vectors (1024 against 1536 dimensions), which cuts index storage by 33%.

side-by-side specs

spectext-embedding-3-smallvoyage-4-lite
providerOpenAIVoyage AI
price$0.02/M$0.02/M
max input8k tokens32k tokens
default dimensions1,5361,024
storage per 1M vectors6.1 GB4.1 GB
acceptstexttext
weightsclosedclosed

same work, both models

workloadtext-embedding-3-smallvoyage-4-lite
index 10,000 help articles~800 tokens each, 8M tokenssame$0.16$0.16
index a 1M-line codebase~10 tokens a line, 10M tokens$0.20$0.20
embed 1M search queries~20 tokens each, 20M tokens$0.40$0.40

at listed rates. re-embedding an index costs the same again.

when to pick which

text-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.

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

voyage-4-lite

Voyage 4 Lite is the latency- and cost-optimized tier of Voyage AI's Voyage 4 embedding series, priced below voyage-4 and voyage-4-large. its embeddings are compatible with the rest of the series, and it costs the same as voyage-3.5-lite.

pick it if

  • you want the Voyage 4 embedding space at a third of voyage-4's price
  • you embed queries cheaply against documents indexed with voyage-4-large
  • you need 256-2048 dimension embeddings over a 32K-token input

skip it if

  • retrieval quality outweighs cost; Voyage reports voyage-4-large 4.80% ahead of it
  • you are indexing source code; voyage-code-4 targets code retrieval

faq

which is cheaper, OpenAI Embedding 3 Small or Voyage 4 Lite?

OpenAI Embedding 3 Small and Voyage 4 Lite cost the same, $0.02/M tokens.

which handles longer documents?

Voyage 4 Lite takes longer inputs (32k tokens against 8k tokens), so it needs less chunking.

can i switch from OpenAI Embedding 3 Small to Voyage 4 Lite without re-indexing?

no. vectors from different embedding models are not comparable, so a switch means re-embedding the whole corpus.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18