V

VOYAGE AI

rerank-2.5

Voyage AI's rerank-2.5 cross-encoder reranker for second-stage retrieval. Multilingual and instruction-following, with up to 32,000 tokens per query-document pair and 1,000 documents per request.

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$0.05Output$0.05

Nbility · embedding group

Input0.04Output0.04

Group prices

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

Usage billing
GroupRatioInputOutput
Base pricex1
0.05/1M
0.05/1M
embeddingx0.8
0.04/1M
0.04/1M

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","messages":[{"role":"user","content":"Hello"}]}'

Compatible endpoints

openaiPOST /v1/chat/completions

Docs for this model

More from Voyage AI