Capabilities
7-day heat trend
+3.3%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 42% of tracked models
- Faster than 70% of tracked models
- Efficiency rank: #546 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About rerank-2.5-lite
Voyage Rerank 2.5 Lite is a lower-cost reranker for latency-sensitive search and RAG pipelines.
rerank-2.5-lite is a Text model from Voyage AI (US). HotON.ai tracks it at $0.02 per 1M input tokens and $0.00 per 1M output tokens, with a 32K-token context window, ~158 tokens/sec throughput and 98.8% availability. Its composite efficiency score is 89/100 at an estimated $0.000 per successful task.
Compare rerank-2.5-lite
Related market news
Frequently asked questions
How much does rerank-2.5-lite cost per 1M tokens?+
rerank-2.5-lite is tracked at $0.02 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.01 per 1M tokens. Figures are illustrative demo data.
What is rerank-2.5-lite best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is rerank-2.5-lite?+
rerank-2.5-lite delivers about 158 tokens/sec with 98.8% tracked availability, suitable for latency-sensitive, real-time applications.
Is rerank-2.5-lite cheaper than other AI models?+
Within the HotON.ai tracked set, rerank-2.5-lite is cheaper than 42% of models on input price and ranks #546 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.