voyage-3.5

voyage-3.5 is a budget-tier language model from Voyage AI. voyage-3.5 is a proprietary model available exclusively through Voyage AI's API. The Voyage family is Voyage AI's model series for this capability tier.

voyage-3.5 is priced at $0.06/1M input tokens. Output token pricing does not apply to this model — it returns a vector or score rather than generated text. At 1,000 tokens per call, voyage-3.5 costs approximately $0.06 per 1,000 API calls.

Its 32K-token context window is sufficient for most production use cases, handling documents up to ~25,000 words or multi-turn conversations spanning dozens of exchanges. Median latency (P50 time-to-first-token) is approximately 80ms — fast enough for real-time interactive applications.

voyage-3.5 is best suited to embedding, search, cost. It is a text-only model without vision or function calling support. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how voyage-3.5 compares to similar models across these dimensions.

voyage-3.5 sits in the budget tier — the most cost-efficient models, best for high-volume simple tasks, classification, extraction, and applications where cost per call is the primary constraint. Unlike open-weights alternatives, voyage-3.5 is only available via Voyage AI's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing voyage-3.5 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.