voyage-code-3vsvoyage-code-4
Both embedding models, compared at each maker’s own API list prices. Every figure links to its source.
Key differences
InputMaker’s official API · global · USD
$0.18 / 1M tokens Voyage AI pricing · as of Nov 1, 2026
$0.12 / 1M tokens Voyage AI pricing · as of Nov 3, 2026
Vector types
float, int8, uint8, binary, ubinary voyage-code-3: more accurate code retrieval with lower dimensional, quantized embeddings – Voyage AI · as of Nov 2, 2026
binary voyage-code-4: code retrieval built for coding agents – Voyage AI · as of Nov 2, 2026
These differences use verified vendor specifications or each maker’s official API on the same region, currency, meter and billing conditions. Different conditions remain side by side in the full table; they do not establish which model is cheaper. Declared features describe support, not measured quality or a recommendation. Missing evidence does not mean a feature is unsupported.
Full comparison
| voyage-code-3 Voyage AI | voyage-code-4 Voyage AI | |
|---|---|---|
| Overview | ||
| Released | Dec 2024 | Aug 13, 2026 |
| Specs | ||
| Dimensions | 1,024 | 1,024 |
| Shortest vector | 256 | 256 |
| Max input | 32K | 32K |
| Vector types | float, int8, uint8, binary, ubinary | binary |
| Pricing | ||
| Price per 1M input tokens | $0.18 | $0.12 |
Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.
Model details and sources
- voyage-code-3 → Available
- voyage-code-4 → Available