VoyageAI by MongoDB: rerank-3-lite
voyageai/rerank-3-litererank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86%...
- Modalities
- text->rerank
- Price
- Free
- Context
- 32K
- Released
- Sep 30, 2026
- Knowledge cutoff
- —
Providers
Every request enters through InfAPI. One key calls every model in the catalog. Upstream groups, ratios, and tiers are not shown.
| Endpoint | Input | Output | Context | Status |
|---|---|---|---|---|
| InfAPI | Free | Free | 32K | Available |
- Input
- Text
- Output
- Rerank
- Tokenizer
- Other
- Max output
- 28,800
- Endpoint
- Chat
Pricing
Listed price for this model on this gateway. Token prices are per 1M tokens.
| Item | Price | Unit |
|---|---|---|
| Inputprompt | $0 | per 1M tokens |
| Outputcompletion | $0 | per 1M tokens |
API
API
The gateway speaks the OpenAI Chat Completions API. Point any compatible SDK at https://infapi.cc/v1 and send the model slug below.
Get your API key
Create a key on the keys page and set it as an environment variable: Keys
export INFAPI_API_KEY=sk-...Make your first request
Use voyageai/rerank-3-lite
import requests
response = requests.post(
"https://infapi.cc/v1/chat/completions",
headers={
"Authorization": "Bearer $INFAPI_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "voyageai/rerank-3-lite",
"messages": [
{
"role": "user",
"content": "Introduce yourself in three sentences."
}
]
},
)
response.raise_for_status()
print(response.json()["choices"][0]["message"]["content"])Endpoint
POST https://infapi.cc/v1/chat/completions
Authorization: Bearer $INFAPI_API_KEY
Using third-party SDKs
Point the OpenAI SDK at https://infapi.cc/v1 with $INFAPI_API_KEY. The HTTP samples above are the request shape this gateway accepts.
from openai import OpenAI
client = OpenAI(
base_url="https://infapi.cc/v1",
api_key="$INFAPI_API_KEY",
)
response = client.chat.completions.create(
model="voyageai/rerank-3-lite",
messages=[{"role": "user", "content": "Introduce yourself in three sentences."}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://infapi.cc/v1",
apiKey: "$INFAPI_API_KEY",
});
const response = await client.chat.completions.create({
"model": "voyageai/rerank-3-lite",
"messages": [
{
"role": "user",
"content": "Introduce yourself in three sentences."
}
]
});
console.log(response.choices[0]?.message?.content);Supported parameters
This model does not publish a parameter list.
FAQ
What is this model?
rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on avera…
How much does it cost?
Free
What inputs and outputs does it support?
text->rerank
When was it released?
Sep 30, 2026