V

VOYAGE AI

rerank-2.5-lite

Voyage AI's rerank-2.5-lite, a lighter cross-encoder reranker tuned for latency-sensitive second-stage retrieval. Multilingual and instruction-following, with the same 32,000-token query-document budget.

Usage billing

Official price vs Nbility

Per 1M tokens, read live from the gateway. Nbility shows its lowest public group.

Voyage AI list price

Input$0.02Output$0.02

Nbility · embedding group

Input0.016Output0.016

Group prices

Every available group is listed with its effective input and output price.

Usage billing
GroupRatioInputOutput
Base pricex1
0.02/1M
0.02/1M
embeddingx0.8
0.016/1M
0.016/1M

Quick start

Replace YOUR_API_KEY with a key from your account.

curl https://api.nbility.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"rerank-2.5-lite","messages":[{"role":"user","content":"Hello"}]}'

Compatible endpoints

openaiPOST /v1/chat/completions

Docs for this model

More from Voyage AI