VoyageAI by MongoDB: rerank-2.5-lite

Origin

voyageai/rerank-2.5-lite

rerank-2.5-lite is a reranker optimized for both latency and quality, delivering a 7.16% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5...

Pricing

Billed at actual usage

Billing follows the provider's own reported cost. The unit prices here are for reference; a model marked "billed at actual usage" has no reliable pre-call price, so your usage page is the record of what you paid.

Call it

Rerank models are served on POST /v1/rerank. Send a query and a list of documents and get them back ranked by relevance; top_n limits how many come back. Billing follows the provider's reported cost.

curl https://macdecloud.com/v1/rerank \
  -H "Authorization: Bearer dcld-sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"voyageai/rerank-2.5-lite","query":"What is the capital of France?","documents":["Paris is the capital of France.","Berlin is the capital of Germany."],"top_n":1}'

Python

The OpenAI SDK has no rerank method; POST with httpx, which the SDK already depends on.

import httpx

resp = httpx.post(
    "https://macdecloud.com/v1/rerank",
    headers={"Authorization": "Bearer dcld-sk-..."},
    json={
        "model": "voyageai/rerank-2.5-lite",
        "query": "What is the capital of France?",
        "documents": ["Paris is the capital of France.", "Berlin is the capital of Germany."],
        "top_n": 1,
    },
)
for r in resp.json()["results"]:
    print(r["index"], r["relevance_score"])