Cheaper Inference
Model record / Voyage AI
rerank-3-lite is available for reranking from Voyage AI. Its reported context window is 32,000 tokens, with up to 32,000 output tokens. Reported inputs: text.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/rerank
curl https://api.cheaperinference.com/v1/rerank \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "rerank-3-lite", "query": "capital of France", "documents": [ "Paris is the capital of France.", "Berlin is in Germany." ] }'Capability source · checked
$0.017 estimated at displayed rates
1,000,000 ÷ 1,000,000 × $0.017
The same billed quantities at the listed reference rates: $0.02.
Input-token charges only at the displayed rate. Chunking and request limits still apply; this is not one request containing a million tokens.
Price quote effective .
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| rerank-3-lite (this model)Voyage AI | $0.017 / 1M input tokens | 32,000 tokens | No |
| rerank-2.5-liteVoyage AI | $0.017 / 1M input tokens | 32,000 tokens | No |
| rerank-2.5Voyage AI | $0.0425 / 1M input tokens | 32,000 tokens | No |
| rerank-3Voyage AI |
This model takes the fields in its sample request. It has no other stated parameters.
See how much this model saves and when its recorded price has been lowest.
This model averaged 11.4% below comparable direct provider prices across the selected range. Its strongest observed window was 2:00 AM–11:00 AM in UTC.
Average saved
11.4%
Cheapest time
2:00 AM–11:00 AM
Hourly coverage
24/24
Signal quality
High
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
—
of 333 ranked models
Last 7 days
—
of 389 ranked models
Last 30 days
#398
of 400 ranked models
| $0.0425 / 1M input tokens |
| 32,000 tokens |
| No |