rerank-2

rerank-2 is a budget-tier language model from Voyage AI. rerank-2 is a proprietary model available exclusively through Voyage AI's API. The Voyage Rerank family is Voyage AI's model series for this capability tier.

rerank-2 is priced at $0.05 per 1M tokens. This is a reranker model billed per 1M tokens rather than per token — token input/output pricing does not apply.

Its 16K-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 120ms — fast enough for real-time interactive applications.

rerank-2 is best suited to reranking, search, rag. 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 rerank-2 compares to similar models across these dimensions.

rerank-2 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, rerank-2 is only available via Voyage AI's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing rerank-2 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.