voyage-code-2vsvoyage-code-3
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
$0.12 / 1M tokens Voyage AI pricing · as of Nov 5, 2026
$0.18 / 1M tokens Voyage AI pricing · as of Nov 1, 2026
Dimensions
1,536 Text Embeddings - Voyage AI by MongoDB - MongoDB Docs · as of Nov 4, 2026
1,024 Voyage AI Embedding and Reranking Models Overview - Voyage AI by MongoDB - MongoDB Docs · as of Oct 30, 2026
Max input
16,000 voyage-code-2: Elevate Your Code Retrieval – Voyage AI · as of Nov 5, 2026
32,000 voyage-code-3: more accurate code retrieval with lower dimensional, quantized embeddings – 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-2 Voyage AI | voyage-code-3 Voyage AI | |
|---|---|---|
| Overview | ||
| Released | Jan 23, 2024 | Dec 2024 |
| Specs | ||
| Dimensions | 1,536 | 1,024 |
| Shortest vector | Not stated | 256 |
| Max input | 16K | 32K |
| Vector types | Not stated | float, int8, uint8, binary, ubinary |
| Pricing | ||
| Price per 1M input tokens | $0.12 | $0.18 |
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-2 → Available
- voyage-code-3 → Available