Calculate the cost of using voyage-code-3 from Voyage for your AI applications
Pricing data last updated:
Mode: Embedding
Max: 32,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
voyage-code-3 is an embedding model from Voyage, one of 21 embedding models they offer. It is priced at $0.18 per 1M input tokens and $0.0000 per 1M output tokens, ranking 134 out of 150 embedding models by cost and cheaper than 10% of models in this category. Its 32K-token context window is in the top 30% among embedding models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 32,000 input tokens.
At $0.18 per 1M input tokens and $0.0000 per 1M output tokens, voyage-code-3 ranks 134 out of 150 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 10% of models in this category.
voyage-code-3 is one of 21 Voyage embedding models, its 32K-token context window places it in the top 30% of embedding models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs voyage-code-3 |
|---|---|---|---|---|
| gemini-embedding-001 | Vertex AI | $0.15 | $0.0000 | -17% |
| gemini-embedding-2-preview | Vertex AI | $0.20 | $0.0000 | +11% |
| gemini-embedding-2 | Vertex AI | $0.20 | $0.0000 | +11% |
Similar embedding models from other providers
No. voyage-code-3 costs $0.18 per 1M input tokens while gemini-embedding-001 costs $0.15 per 1M input tokens, making gemini-embedding-001 17% more affordable for input. However, voyage-code-3 may offer different capabilities or performance characteristics that justify the price difference.
voyage-code-3 input pricing is $0.18 per 1M tokens, which is 80% above the median of $0.10 for embedding models. It ranks 134 out of 150 embedding models by input cost, making it cheaper than 10% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.02.
Among Voyage's 21 embedding models, voyage-code-3 ranks 20 by input cost.
The most comparable embedding models to voyage-code-3 are: gemini-embedding-001 from Vertex AI ($0.15/1M input tokens); gemini-embedding-2-preview from Vertex AI ($0.20/1M input tokens); gemini-embedding-2 from Vertex AI ($0.20/1M input tokens); gemini-embedding-001 from Google Gemini ($0.15/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
voyage-code-3 supports up to 32,000 input tokens, placing it in the top 30% of embedding models by context window size (rank 27 of 133). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
voyage-code-3 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.18 and generating 1M output tokens costs $0.0000.